#cat x yann

[orangecat30]

Taste

lmao.

[yors-truly]

9 People You Want to Get to Know Better

Major thanks to @ddbirb for the tag :)!! In exchange, I'll tag @boowhumps, @cosycaracal, @ioncedreamedaflower, @minutiaewriter, @eli-writes-sometimes, and whoever else wants to partake to fill the gaps bc i actually dont have a ton of tags ;;;

3 ships:

#1: Soundwave x Shockwave (Transformers)

This ship is actually a lot more rare than I first assumed. Whenever I go digging up content of it, there's usually small rations here and there. No where enough to feed me but more than enough to appreciate.

I know for a fact that what I have to say about them won't do my perception much justice, as there's so much I could and want to dabble on, but I've been obsessed with this ship in particular, not because of my current Decepticon fixation (well, yes, because of that), but it seems kinda fitting, if that makes sense?? I also like the idea of a tsundere Soundwave and a Shockwave in denial (because its "ilLoGiCAl" or whatever lol), and the thought of just, y'know, two introverts being lucky enough to stumble upon and love each other in such a way is adorable to me :')

That was a little ramble-y. uhh... i won't do the same with the others dont worry.

#2: Polymorphic/Vladimir x Vyrus (Databrawl)

I recently learned that people tend to get annoyed at this one because others call Vladimir a "simp" for Vyrus, but hear me out.

I've been wanting to get into Databrawl for the longest time now and study its lore, and from what I've encountered so far, I actually like their potential over anything else in this ship. I don't know about you, but I don't think there's anything more romantic than devoting your loyalty to someone, all while agreeing to help them conquer their (albeit, innocent) enemies and making sure they see their way through things. I love ships like that!

Not to mention that it's literally cannon that Vladimir is Vyrus's favorite Corruption. If we're talking about shipping, then this one's got the most important luggage, for sure X)

#3: I can't think of a third one, sorry :( (at least not one that isn't my OCs. If I could, it'd probably be related to warrior cats lol)

Last song:

haunt me (x3) by Teen Suicide. In fact, I'm listening to it right now as I type this out. What a coincidence!

Last movie:

Disney/Pixar Cars (2006). I walked in to my brother's room while he was watching it and, of course, I was glued to the screen :)

Last book:

Yann Martel's Life of Pi. I'm reading it for my English class and I LOVE it so far! Currently on chapter 9.

Currently consuming:

Heat. I'm freezing.

Currently craving:

Heat. I'm freezing.

[yeaaahhhsss]

Book I’ve Read!

These are titles I’ve read so far as my memory can recall! I do still remember the first novel I read (but not sure it really was the first or the first touching my heart...) so yeah this is it! (not in an orderly manner)

Fiction 1. Herr der Diebe (The Thief Lord) by Cornelia Funke 2. Harry Potter Series by J. K. Rowling (- The Philosopher’s Stone and The Order of The Phoenix 3. The Mortal Instruments Series by Cassandra Clare (only City of Bones and City of Glass) 4. Catching Fire by Suzanne Collins 5. A Series of Unfortunate Events by Lemony Snicket (only The Wide Window and The Penultimate Peril) 6. Legend of Great Tang’s Twin Dragons by Huang Yi 7. The Hundred-Year-Old Man Who Climbed Out of The Window and Disappeared by Jonas Jonasson 8. Sherlock Holmes Series by Sir Arthur Conan Doyle • Sign of Four • The Adventures of Sherlock Holmes: The Five Orange Pips • The Return of Sherlock Holmes: The Adventures of Empty House, ...of Norwood Builder, ...of Dancing Men, ...of Six Napoleons, ...of the Goldern Pince-Nez • His Last Bow: The Adventure of Wisteria Lodge, ...of the Bruce-Partington Plans, ...of Lady Frances Carfax • The Case-Book of Sherlock Holmes: The Adventure of the Three Garridebs 9. Jack Nightingale Series by Stephen Leather (Nightfall, Midnight, and Lastnight) 10. The Catcher In The Rye by J.D. Salinger 11. To Kill A Mockingbird by Harper Lee 12. The Brother Karamazov by Fyodor Dostoyevsky 13. On The Road by Jack Kerouac 14. Wuthering Heights by Emily Brontë 15. Le Petit Prince by Antoine de Saint-Exupéry 16. Notes From Underground by Fyodor Dostoyevsky 17. Book of Souls by Glenn Cooper 18. The Time Keeper by Mitch Albom 19. The First Phone Call from Heaven by Mitch Albom 20. Love Letters to The Dead by Ava Dellaira 21. Ways to Live Forever by Sally Nicholls 22. Life of Pi by Yann Martel 23. The Perks of Being A Wallflower by Stephen Chbosky 24. The Universe of Us by Lang Leav 25. Hamlet by William Shakespeare 26. 

Comic books 1. Slam Dunk by Inoue Takehiko 2. Detective Conan by Aoyama Gosho 3. Interstellar Bridge/Seikan Bridge by Kyukkyupon 4. Hunter x Hunter by Yoshihiro Togashi 5. Yuyu Hakusho by Yoshihiro Togashi 6. Death Note by Tsugumi Ohba 7. Bakuman by Tsugumi Ohba 8. Kuroko’s Basketball by Tadatoshi Fujimaki 9. Nozaki by Izumi Tsubaki 10. Haikyuu!! by Haruichi Furudate 11. Kocchi Muite! Miiko by Eriko Ono 12. Fullmetal Alchmeist by Hiromu Arakawa 13. Solanin by Inio Asano 14. A Man and His Cat by Umi Sakurai 15.

Nonfiction 1. Blue Collar, Blue Scrubs by Michael Collins, MD. 2. Ceci est ma femme by Oliver Sacks 3. The 5-Second Rule by Mel Robbins 4. Blink! by Malcolm Gladwell 5. David and Goliath by Malcolm Gladwell 6. What The Dog Saw by Malcolm Gladwell 7. The 7 Habits of Highly Effective People by Stephen Covey 8. Guns, Germs and Steel by Jared Diamonds 9. When by Daniel H. Pink 10. The Order of Time by Carlo Rovelli 11. The Problems of Philosophy by Bertrand Russel 12. The View from Planet Earth by Vincent Cronin 13. Collapse by Jared Diamond 14. How to Lead When Your Boss Can’t or Won’t by J. C. Maxwell 15. Aristotle’s Children by R. E. Rübenstein 16. Atomic Habits by James Clear 17. The Naked Traveler 3 & 4 by Trinity 18. 

[yeoldontknow]

💌interview tag

tagged by the loveliest, brightest angels @chillingkoo and @onherwings to do this fun tag. thank you so so much my loves!!

Rules: answer the questions and tag 20 blogs you are contractually obligated to know better!

Name/nickname: kat

Pronouns: she/her

Star sign: aquarius sun, leo moon, aries rising

Height: 162cm or 5′4″

Time currently: 9.29am

When is your birthday: january 23

Favourite band/groups: kpop - exo, tvxq, bts, monsta x, shinee, twice, itzy, ateez, knk, cix, exid, sistar, seventeen

other: tool, puscifer, IAMX, white lies, elbow, ghost, nothing but thieves, official hige dandism, deftones, nick cave & the bad seeds, readiohead, the cure etc etc this list is endless

Favourite solo artist: kpop - chanyeol solo works, chung ha, lee hi, iu, jongdae solo works, wonho

other: uppermost, xavier omar, masago, sza, doja cat, mansur brown, laurel, david bowie, prince, patrick watson, elijah blake, harry styles

Song Stuck in Your Head: comptine d’un autre ete l’apres midi - yann tiersen

Last Movie You Watched: pieces of a woman (oof, i dont even know if i enjoyed it but damn)

Last Show You Binged: the night stalker documentary

When You Created Your Blog: april 30, 2017

Last Thing You Googled: asus z97-e (im building a computer and my dad  keeps giving me parts he has lying around lmao)

Other Blogs: @yeoldontknowiread - my fic recs blog

Why I chose my url: because....yeol does not, in fact, know that i write all this fanfiction lmao (at least i hope???)

Do you get asks: sometimes! sometimes theres a bunch, other times theres none for a while. sometimes theres pressuring asks and other times theres things i just delete because i dont want the energy on my blog. its a grab bag really

How Many People Are You Following: 350

How Many Followers Do You Have: some

Average Hours of Sleep: god this also depends...on the weekday, around 5-7 (the weighted blanket helps so much i actually normally get that 7 unless its a really bad anxiety day. can you believe im up from 3-4???) on the weekends its about 10 or 11

Lucky Numbers: 16, 61

Instruments: violin and voice. i can sight read basic piano so long as i can find middle c. some guitar but not enough to be proficient

What I’m Currently Wearing: old university sweatpants, my “hex the racists” t-shirt, and a purple zip hoodie

Dream job: music supervision for major motion pictures; published author; subtitle operations at netflix; some other off the wall creative job that allows me to travel, make art, write, take photos, eat food with some sense of stability and health insurance lmao

Dream trip: go back to japan to see the north (hokkaido) and the south (fukuoka or kagoshima); australia/new zealand; hawaii

Favorite food: asian food hands down. korean, indian, japanese, arab, armenian - truly, its all so comforting and filling for me. i love it so much. its a warmth that comes from inside.

Favorite song: asjfdoiajfo? how am i meant to pick just one?? uh....ill go with the song im obsessed with right now -- The Bones of a Dying World - If These Trees Could Talk

Top Three Fictional Universes You’d Like To Live In: omg lmaooo probably post war harry potter; sailor moon; any ghibli world

tagging: @yehet-me-up @jamaisjoons @yoonia @shadowsremedy @kyungseokie @jenmyeons @j-pping @delhyun @loeybeans @kimtaehyunq @ditzymax @yeojaa @snackhobi @sahmfanficbts @hobi-gif @xjoonchildx @bratkook @imdifferentshadesofpurple @softyoongiionly @jinterlude and anyone else who wants to do this! as always please only do so if you wish!

[wjmild]

A to Z Book Rec for Isolation

A

and the mountains echoed by khaled hosseini 

generational novel of a family in Afghanistan 

B

the birth of venus by sarah dunant

a young painter girl in florence during the fall of the medici’s and the religious revolution 

C

children of blood and bone by tomi adeyemi

magic was taken from the people and they want it back. heart-wrenching characters and fast paced story telling. 

D

darker shade of magic by v.e. schwab 

magicians can travel between alternate universes of London and absolutely no one is using this magic for the right reasons

E

everything, everything by nicola yoon

a girl who has a disease where if she left her home anything could make her sick. then she meets a boy

F

fruit of the drunken tree by ingrid rojas contreras 

two young girls in the 90s of Colombia on different sides of the capitalist world find an unlikely friendship

G

good omens by neil gaiman 

an angel and a demon try to stop the apocalypse but they lose the antichrist 

H

high mountains of portugal by yann martel 

a man finds a treasure map in Lisbon and goes on a long adventure to discover that maybe love was the real treasure after all.

I

illuminae files by amie kauffman and jay kristoff 

space adventure of found family and morally grey astronaut kids who try to stop their spaceships from blowing up or infecting everyone 

J

the map of salt and stars by zeyn Joukhadar

side-by-side of interconnecting stories that are 800 years apart between a young Syrian refugee and a mapmaking girl 

K

knife of never letting go by patrick ness

everyone can hear what men are thinking, but no one can hear the women... if there were women. too bad the men killed them all... haha UNLESS

L

last true poets of the sea by julia drake 

girl is sent to live with uncle after traumatic family incident. she hates it. then she loves it. wlw and ocean diving in one!

M

maggot moon by sally gardner

very interesting writing style about a boy who wants to stop the totalitarian regime who threatens his family and friends

N

the namesake by jhumpa lahiri

an indian boy grows up in america and has fundamental differences with his parents who wish he was more traditional

O

the oresteia by aeschylus 

revenge times 5? dad kills daughter, mom kills dad, son kills mom, country exiles son, a lot of other people die. its insane and a legal nightmare where everyone’s actions are grey

P

princess bride by william goldman

girl loves boy. boy dies. girl has to marry bad prince. true love prevails!

Q

the conQueror’s saga by kiersten white

takes place during the ottoman regime and their surrounding neighbors. friends to lovers to enemies to lovers to friends? and sibling issues are also addressed

R (too many options)

raven cycle by maggie stiefvater

group of friends tries to find a dead welsh king and try not to get themselves killed as they mess with a lot of magic

rules of magic by alice hoffman

family of witches has to avoid love but they are not very good at it

red rising by pierce brown

color-coded space society that goes through a rebellion led by a lowest Red who turns TOP Gold

S (same as R)

starless sea by erin morgenstern 

underground library and stories that are not just stories and people who are and are not just people

song of achilles by madeline miller

gay iliad fanfiction 

six of crows by leigh bardugo

the ultimate heist / found family trope

T

travelling cat chronicles by hiro arikawa

cat follows owner to the ends of the earth only for things to end in tragedy. this book made me cry for five hours, you’ve been warned.

U

unmarriageable by soniah kamal

pride and prejudice but it takes place in Pakistan and its very feminist

V

villains duo by v.e. schwab 

two college idiots give themselves superpowers and they don’t necessarily use them for good

W

winternight trilogy by katherine arden 

all the russian myths are true and they are dying because christianity is making them obsolete. a young girl helps the king of winter to save them.

X

a very large eXpense of sea by taherah mafi 

a brown girl after 9/11 is racially profiled a lot and then she meets a white boy. better than it sounds

Y

the young elites by marie lu

magical teenagers in a dark dark fantasy novel

Z

the serpent king by jeff Zentner

a pastor’s son is hated by a lot after his family falls to scandal and he relies a lot on his two friends. this obviously ends badly

[rosequart]

Rose Quartz

send me a character!

favorite thing about them

she’s so deeply tragic and mysterious and multifaceted (lol) in such an interesting way. the fact that she was known to be so loving that she cried when other crystal gems got hurt, but also had trouble understanding and expressing love (greg), thats so GOOD that’s such good characterization! it’s rare to see a character like this in any form of media

i want to see soo many more flashbacks (whatever’s in the chest?), but i also wouldn’t mind if we didn’t get too many, since the last episode really hammered home the whole “let rose rest you bastards” thing

least favorite thing about them

the fact that she bubbled bismuth still stings :^( she’s done a lot of bad shit but this is much more personal + morally unambiguous

favorite line

“i’m…not a real person” mood to end all moods!

brOTP

amethyst (you KNOW she was fascinated by this quartz who wasn’t born knowing a purpose, and she would let ame do whatever she wanted and be like :^D way to go!). also this will never happen but i want her to meet peridot…she would LOVE this small green gem

OTP

greg!

nOTP

well. she IS dead so there isn’t much out there for her re: shipping lol

random headcanon

she would love shrek a lot. i think she would love all human pop culture, completely unironically

“what’s that? warrior cats? …earth animals, having a society and battling each other? i don’t understand but wow!”

unpopular opinion

some people have a really hard time conceptualizing rose and why she did x and like…i don’t know, i think she’s a very complex character but her motivations were simple! at her core she just wanted to desperately leave a terrible home and be with a more loving family :^((( and i feel like people have to say “i don’t excuse her actions but…” more for rose than the rest of the diamonds which makes me sad! or something!!

song i associate with them

a quai — yann tiersen

favorite picture of them

>:3c

and bonus She

[blacknerdproblems]

White Boy Rick is exactly that: White. Boy. Rick. The film directed by Yann Demange based on the true story of Rick Wershe Jr. the youngest FBI informant in history. I love when a story about a white drug dealer is him ratting out the black guys…said black people never. I know it is a true story, so I can’t really get mad at the turn of events; I mean I can, but… that’s just Black Life Problems right there.

The film follows Rick Wershe Jr.’s introduction into drug dealing via the FBI. Rick’s father, a known gun dealer in Detroit, is under scrutiny for… well… selling guns. The FBI uses this to trap Rick into being an informant in their “war on drugs” in the city. They wanna take down the crime boss Johnny ‘Lil Man’ Curry – Black guy played by Johnathan Majors. Now I’m not saying dang it’s always the white man taking down the black man, I mean they were all drug dealers, but the white man DID help take down the Black man. Again, I can’t really criticize the story, I mean that ish happened, what I can do is talk about the storytelling and the effect of these sides of stories being told with their foundation being black life.

Bendin’ Corners and Camera Angles

First off the movie is remarkable. It is shot well, the performances are engaging and strong, I was in it from beginning to end. I felt things for the characters, laughed, could not bring myself to cry because I physically cannot cry white tears, but it was emotionally provoking. Richie Merritt, the actor playing Rick, did a fantastic job in his breakout role. Matthew McConaughey, in the role of Ricky’s father, Richard Wershe Sr.: got to play that guy he likes to play where he’s f#$*ing up but trying his best and then works real hard to correct something he can never actually correct. Plus, he has a slick pseudo mullet in this one. No judgement in that assessment, he does a great job.

The film is funny when it needs to be. I’ll have to get my Detroit friends to weigh in on the accurate portrayal of Detroit in the late 80s but the environment felt real. I mentioned the foundation of this tale is black life, because it always is. Since slavery happened, the foundation of anything really in this country is black life. I was glad the movie did not ignore this, at a few turns in the film the black characters go in on how differently Rick is treated in the system than them, and warned him not to get them F*%ked…awkward.

White Boy Rick Wannabe Black

I say from experience growing up with white kids who wished they were black or, at the basest form, wished they were White Boy Rick. This is exactly how I picture a kid growing up influenced by his real surroundings. The movie has a way of showing you poor white existence that brings perspective. Rick is rolling with the fat cats and they are drug lords who, of course, are black. You might recognize one of the key drug dealers who becomes Rick’s close friend, Rudell ‘Boo’ Curry, the role played by RJ Cyler – yup the blue ranger from the Power Rangers reboot. You also see well known rapper YG play a role as Leo ‘Big Man’ Curry – a pretty funny cameo actually.

It was nice to see Black people living it up with the juxtaposition of the poor white family struggling with drug addiction and surviving. BUT as White people do, they used Black people and the business they were running to get ahead themselves. Rick even has some moments with the kingpin’s wife, Cathy Volsan-Curry played by Taylour Paige (Hit The Floor). Not a good move. It was such a true telling of how privilege can prevail for white people at anytime.

Read on here. [x]

[incompletedolphin]

Playlist Snooping Tag

tagged by @discoball-deaky

Rules: we're snooping on your playlist. Put your entire music library on shuffle and list the first ten songs, then choose ten victims!

Renegades by X Ambassadors

Feel it still by Portugal. the Man

Like Toy Soldiers by Eminem

7 rings by Ariana Grande

Stronger than Me by Amy Winehouse

Tie your mother down by Queen

Sad Lisa by Cat Stevens

La valse d'Amelie by Yann Tiersen

One point perspective by Arctic Monkeys

She wants to (Get on down) by Bill Withers

[orangecat30]

CAT X YANN

[daisystudies]

40 summer reading list ideas

looking for something to read over the summer? whether you’re looking for a casual beach read or something to spend all day reading, here’s some of my favorites that I’ve read in past summers.

1. The Glass Castle by Jeannette Walls

2. The Secret Life of Bees by Sue Monk Kidd

3. A Thousand Splendid Suns by Khaled Hosseini 

4. Cat’s Cradle by Kurt Vonnegut

5. 11/22/63 by Stephen King

6. Half Broke Horses by Jeannette Walls

7. The Handmaid’s Tale by Margaret Atwood

8. The Kite Runner by Khaled Hosseini

9. The Stranger by Albert Camus

10. Catcher in the Rye by J.D. Salinger

11. A Moveable Feast by Earnest Hemingway

12. IT by Stephen King

13. The Great Gatsby by F. Scott Fitzgerald

14. Of Mice and Men by John Steinbeck

15. Animal Farm by George Orwell

16. I Am Malala by Malala Yousafzai

17. Life of Pi by Yann Martel

18. Brave New World by Aldous Huxley

19. The Alchemist by Paulo Coelho

20. East of Eden by John Steinbeck

21. On the Road by Jack Kerouac 

22. The Color Purple by Alice Walker

23. Diary of an Oxygen Thief by Anonymous

24. Out of Africa by Karen Blixen

25. Things Fall Apart by Chinua Achebe

26. Les Miserables by Victor Hugo

27. Adventures of Sherlock Holmes by Sir Arthur Conan Doyle

28. Little Women by Louisa May Alcott

29. Emma by Jane Austen

30. Anna Karenina by Liev Tolstói

31. Hidden Figures by Margot Lee Shetterly

32. Jane Eyre by Charlotte Bronte

33. Frankenstein by Mary Shelley

34. The Metamorphosis by Franz Kafka 

35. To Kill a Mockingbird by Harper Lee

36. The Canterbury Tales by Geoffrey Chaucer

37. The Iliad by Homer

38. In Dubious Battle by John Steinbeck

39. Grapes of Wrath by John Steinbeck

40. The Underground Railroad by Colson Whitehead     

i made an ap lit reading list a bit ago which you can find here!

hope you guys enjoy! if you read any of these lmk what you think x 

[alystayr]

Playlist musicale 2019 (1/2)

Liste des chansons (playlist 2019 - part. 1)

Mise à jour : 30 juin 2019

playlist 2019 (part. 1)

playlist 2018 (part. 2), playlist 2018 (part. 1)

playlist 2017 (part. 2), playlist 2017 (part. 1)

playlist 2016 (part. 2), playlist 2016 (part. 1)

playlist 2015

0-9 #

A

A Perfect Circle - So Long, And Thanks For All The Fish (2018)

AC/DC - For Those About to Rock (We Salute You) (1981)

Air - La Femme d'Argent (1998)

Alice In Chains - Angry Chair (1992)

Alt-J (feat. GoldLink) - Last Year (Terrace Martin Version) (2018)

Arcade Fire - We Exist (2013)

Archive (feat. Band Of Skulls) - Remains Of Nothing (2019)

Asaf Avidan - Over You Blues (2010)

B

Joan Baez - Diamonds and Rust (1975)

Balthazar - Bunker (2015)

Band of Horses - Wicked Gil (2006)

The Beatles - Helter Skelter (1968)

Beirut - The Rip Tide (2011)

Björk - Army Of Me (1995)

Frank Black - Los Angeles (1993)

The Black Keys - Lo/Hi (2019)

The Blaze - Queens (2018)

Bon Iver - Holocene (2011)

David Bowie - The Stars (Are Out Tonight) (2013)

Dave Brubeck - Take Five (1959)

Jeff Buckley - Last Goodbye (1994)

Kate Bush - The Man I Love (1994/1927)

C

Francis Cabrel - Samedi Soir Sur La Terre (1994)

Cage The Elephant - Ready To Let Go (2019)

Bertrand Cantat - Les pluies diluviennes (2017)

Lewis Capaldi - Bruises (2017)

The Cardigans - Erase / Rewind (1998)

Nick Cave & the Bad Seeds - O'Children (2004)

Chubby Checker - Let's Twist Again (1961)

Cigarettes After Sex - Crush (2018)

Gary Clark Jr - This Land (2019)

Leonard Cohen - Avalanche (1971)

Vladimir Cosma - Les compères (1983)

The Cramps - Human Fly (1983)

The Cranberries - All Over Now (2019)

The Crystals - Da Doo Ron Ron (1963)

D

Dick Dale & The Del-Tones - Pumpkin and Honey Bunny / Misirlou (from Pulp Fiction) (1994/1962)

The Dead Weather - Hang You From The Heavens (2009)

Depeche Mode - It’s No Good (1997)

Détroit - Sa majesté (2013)

Dido - Take You Home (2019)

Dire Straits - Private Investigations (1982)

The Dø - Anita No! (2014)

Peter Doherty & The Puta Madres - Who's Been Having You Over (2019)

Lou Doillon (feat. Cat Power) - It's You (2019)

Dolly - Fin d'époque (1997)

Bob Dylan - Knockin' On Heaven's Door (1973-1995)

E

Eels - Tremendous Dynamite (2009)

Eiffel - N’aie rien à craindre (2019)

Eiffel - Ne respire pas (2002)

Eminem - Lose Yourself (2002)

F

Mylène Farmer - Sentimentale (2018)

Florence + The Machine - Hunger (2018)

Foals - Exits (2019)

Foo Fighters - All My Life (2002)

G

Peter Gabriel - Growing Up (2002)

Serge Gainsbourg - La Javanaise (1963)

Garbage - Stupid Girl (1995)

Genesis - Dancing with the Moonlit Knight (1973)

The Good, The Bad & The Queen - Merrie Land (2018)

Macy Gray - Sugar Daddy (2018)

Greta Van Fleet - Highway Tune (2017)

H

Françoise Hardy - Tous les garçons et les filles (1962)

Ben Harper - Diamonds on the Inside (2003)

PJ Harvey - This Is Love (2000)

Hole - Awful (1998)

Buddy Holly - Peggy Sue (1957)

David Holmes - Rodney Yates (1997)

I

IAM - La fin de leur monde (2007)

Imagine Dragons - Natural (2018)

Indochine - J'ai demandé à la lune (2002)

Billy Idol - Dancing With Myself (1981)

Les Innocents  - Jodie (1987)

Interpol  - If You Really Love Nothing (2018)

Iron Maiden - Fear of The Dark (1992)

J

Jean Michel Jarre - Robot’s Don’t Cry (movement 3) (2018)

Elton John - I'm Still Standing (1983)

Joy Division - Transmission (1979)

K

The Kills - Black Balloon (2008)

The Knife - Heartbeats (2003)

Cecilia Krull - My Life Is Going On (from La Casa de Papel) (2017)

L

Lake Street Dive - Mistakes (2016)

Mark Lanegan & Isobel Campbell (cover The Gun Club) - The Breaking Hands (2012)

Led Zeppelin - Dazed And Confused (1969)

LP - One Night In The Sun (2018)

M

M - Lettre infinie (2019)

Madness - One Step Beyond... (1979)

Ibrahim Maalouf - Beirut (2011)

Madrugada - Hold on to you (2005)

Manu Chao - Me llaman calle (2007)

Massive Attack - Angel (1998)

Mercury Rev (Feat. Norah Jones) - Okolona River Bottom Band (2019)

Metallica - Fade to Black (1984)

Miossec - Nous sommes (2018)

Moby - Extreme Ways (from Jason Bourne) (2002)

Tom Morello (feat. Gary Clark Jr. & Gramatik) - Can't Stop The Bleeding (2019)

MorMor-  Heaven's Only Wishful (2018)

Giorgio Moroder - Midnight Express Theme - The Chase (1978)

Mudhoney - Touch Me I'm Sick (1988/2013)

Muse - Madness (2012)

N

The National - Hairpin Turns (2019)

New Order - Blue Monday (1983)

Nine Inch Nails - March Of The Pigs (1994)

Nirvana - Aneurysm (1991)

No One Is Innocent - Charlie (2015)

Claude Nougaro - Paris Mai (1968)

O

Agnes Obel - Riverside (2010)

Les Ogres de Barback - P'tit coeur (2019)

J.S. Ondara - American Dream (2019)

OrelSan (feat. Stromae) - La pluie (2017)

P

Pink Floyd - On The Turning Away (1987)

Placebo - Protège Moi (2003)

Planes Mistaken For Stars - Fucking Tenderness (2016)

The Platters - The Great Pretender (1955)

The Police - Every Breath You Take (1983)

Portishead - Sour Times (1994)

Elvis Presley - All Shook up (1957)

The Prodigy - Firestarter (1997)

Q

Queen - Love Of My Life (1975)

Queens Of The Stone Age - The Lost Art Of Keeping A Secret (2000)

R

The Raconteurs - Sunday Driver (2018)

Radiohead - Paranoid Android (1997)

Rag'n'Bone Man - Human (2017)

Rage Against The Machine - Take The Power Back (1991)

Ramones - I Wanna Be Sedated (1978)

R.E.M. - Bad Day (2003)

Chris Rea - Cry for Home (2005)

Lou Reed - Satellite of Love (1972)

Rival Sons - Feral Roots (2019)

Dick Rivers - Pas de vainqueur (2014)

Cock Robin - The Promise You Made (1985)

The Ronettes - Be My Baby (1963)

S

Saez - Rue d'la soif (2017)

Nitin Sawhney - Sunset (2001)

The Score - Stronger (2019)

Eric Serra - My Lady Blue (from Le Grand Bleu) (1988)

Sex Pistols - God Save The Queen (1977)

Shaka Ponk - Killing Hallelujah (2018)

Sigur Rós - Brennisteinn (2013)

Emilie Simon - Fleur De Saison (2006)

Simple Minds - Alive And Kicking (1985)

Siouxsie And The Banshees - Israel (1983)

Skunk Anansie - Charlie Big Potato (1999)

The Smashing Pumpkins - Zero (1995)

Patti Smith - Summer Cannibals (1996)

Sonic Youth - Mildred Pierce (1990)

Soundgarden - Fell On Black Days (1994)

Regina Spektor - All The Rowboats (2012)

Bruce Springsteen - Western Stars (2019)

Still Corners - The Trip (2003)

Alain Souchon - Quand j'serais KO (1988)

Angus & Julia Stone - Heart Beats Slow (2014)

The Stooges - Ann (1969)

Supertramp - Cannonball (1985)

Survivor - Eye Of The Tiger (1982)

System Of A Down - Toxicity (2001)

T

Talk Talk - Such A Shame (1984)

Sébastien Tellier - La Ritournelle (2004)

Téléphone - Argent trop cher (1980)

Kate Tempest - Perfect Coffee (2016)

These New Puritans - Into The Fire (2019)

Hubert-Félix Thiéfaine - Confessions d'un Never Been (2005)

Yann Tiersen - Tempelhof (2019)

Thievery Corporation - Shadows of Ourselves (2000)

Tina Turner - What's Love Got To Do With It (1984)

U

U2 - New Year’s Day (1983)

V

Frankie Valli - Can't Take My Eyes off You (1967)

Suzanne Vega - 12 Mortal Men (2016)

The Velvet Underground - Femme Fatale (1967)

Veruca Salt - Volcano Girls (1997)

The Verve - The Drugs Don't Work (1997)

Le Villejuif Underground - Villejuif Underground (2017)

W

Weezer - Zombie Bastards (2019)

The Who - My Generation (1965)

John Williams - Hedwig's Theme (From Harry Potter and the Sorcerer's Stone) (2001)

Amy Winehouse - Love Is A Losing Game (2006)

Wolf Alice - Don't Delete the Kisses (2017)

Woodkid - Run Boy Run (2013)

Shannon Wright - The Caustic Light (2013)

X

XTC - Making Plans For Nigel (1979)

Y

Neil Young - Southern Man (1970)

Z

Hindi Zahra - Stand Up (2009)

Zazie - Nos âmes sont (2018)

[ghiblicottage]

tagged by: @minyardx​ thank yoouuu angel 💓

rules: list your favorite band or artist for each letter of the alphabet. tag people whose musical taste you want to know better!

A – amy whinehouse / B – bon iver / C – cat stevens / D – daft punk / E – elliott smith / F – fleetwood mac / G – grace vanderwaal / H – harry styles / I – in love with a ghost / J – janis joplin / K – kwamie liv / L – lana del rey / M – moriarty / N – noir désir / O – of monsters and men / P – pink floyd / Q – queen / R – ramin djawadi / S – sufjan stevens / T – tame impala / U – x / V – x / W – the weeknd / X – the xx / Y – yann tiersen / Z – x

tagging: @apotter​ @aredhels​ @queeniegoldtsein​ @hazelevans​ @slytheri-nn​ @padmcdala​ @ginevramolly​ @jamescarstairss @vlctorvale @rickonstvrk ✨(only do it if you feel like it!)

[loveyourlocalgirlgang]

INTERVIEW GIRL GANG - #6 WICKED GIRLS - Lyon

Un collectif européen de filles mélomanes, engagées sur des sujets sensiblement féminins et épineux, loin d’être lisse. : soirées et blog et action artistiques. Wicked Girls est né en 2011, de la rencontre de Dj Carie et Melle Lau. Les deux comparses étaient parties du constat que la musique jouée et produite par des femmes manquait cruellement de promotion. L’année suivante elles avaient rallié une équipe, ce collectif s’est constituée en asso, des événements ont suivi tout naturellement. 5 années d’organisations de concerts et de programmation de Djs ! 

Sixième portrait de la série dédiée aux girl gangs sur le site …. ♀️

Pouvez-vous nous raconter le parcours et les activités de Wicked Girls  ?

ça commence par la rencontre de Dj Carie et moi même (Lau)  à un apéro et ce jour-là on a l'idée un peu folle de se dire : on lance un blog pour promouvoir la musique faite par des femmes ?

On est en 2011 et  c'est la grande arrivée de MIA - SANTIGOLD - RYE RYE, des femmes engagées et qui donnaient une image de warrior.  

Carie part quelques mois plus tard pour le Canada, ça aurait pu bien faire patiner le projet mais j'ai pas paniqué et j'ai ouvert le blog le lendemain de notre rencontre  ! 

En 2012 on commence à organiser nos propres soirées, désespérant de voir si peu de femmes sur les line ups. La fée verte (Lyon) Le Baraka (Clermont-fd) jusqu'à une résidence au 101 (Clermont-Ferrand), où là nous avons eu le temps de développer une programmation. Depuis 3 ans maintenant, on a la chance d'avoir une résidence à La MM à Lyon en bas des pentes de Croix Rousse, Carie s'active aussi à La Casa indépendente à Lisbonne et on va faire notre grande première à Marseille au Cabaret Aléatoire. Aujourd’hui on concentre notre énergie sur les soirées et le rassemblement de djs féminines activistes de la Global Beat.

On s'attache à raconter un monde musical qui deviendrait plus coloré et paritaire !

Qui fait partie du collectif , est-il ouvert au "grand public"? 

Le noyau dur c'est Carie, Bolly Cat et moi même, les copines qui rejoignent l'aventure nous sont très très proches : Maureen Lem (Paris) - Mambo Chick (Annecy) - Mariana (São Paulo) - Paloma Colombe (Paris-Alger) - Caroll (Lille) -

Il est évidemment ouvert à toutes les personnes qui souhaiterait rejoindre le collectif  :) Et on adore rencontrer des nanas qui musicalement nous ressemblent. 

Le seul point fédérateur étant que l'on est clairement positionnées sur la scène Bass music- Global Beat- Tropical.  On a des tas de copines qui font ça très très bien pour la Techno, nous on se concentre sur nos amours pour les grosses bass :)

On parle souvent de la misogynie dans la musique, l'art, la culture... . Vous  sentez-vous investies d’un rôle par rapport à ça ? 

On combat réellement ça. C'est tout de même incroyable en 2019 d'être encore dans un monde ou le patriarcat écrase les projets féminins, que ce soit implicitement ou explicitement. 

Idéalement les line ups 100% féminins on s'en passerait bien, mais la réalité c'est que tu découvres chaque jour un autre festival, une autre soirée ou il n'y a même pas une fille sur le plateau. La réalité est celle-là, et tant qu'il le faudra on continuera à programmer des plateaux exclusivement féminins.

On est aussi vigilante aux autres domaines, mais on a pas la prétention de pouvoir agir partout alors on se concentre sur le son ;)

Vous vous définissez comme une  association féministe ? qu'est-ce-que cela implique pour vous ?

C’est drôle, quand on a commencé on nous "traitait" de féministe, tu sais le gros mot : méchante hystérique de féministe qui veut écraser les burnes de l'homme dominant, et on savait jamais comment s'en sortir :)

On a grandit depuis et on assume totalement être féministe :) ça implique d'être sans arrêt en veille, tant de lectures que de rencontres que de conférences, de s'entourer des bonnes personnes et de travailler au mieux dans sa vie pro, perso et de wicked à transmettre les meilleures valeurs qui soient.

Vos artistes préféré.e.s du moment ?

Alors on préfère toujours parler de meufs, mais tout confondu ça donne : Mafalda, Bonaventure (qu'on programme toutes les deux à Marseille) mais aussi Bad Sista, Madam X, Jamz supernova, Voilaaa, Skeptical, Stromzy, JLin, A-wa,  Batida, Little simz,  Leikeli47, mais aussi Henry Wu, Nubya Garcia, Mayra Andrade, Les Filles de Illighadad... 

Avec quel  artistes aimeriez-vous collaborer ?

Supafly crew Bruxelles, ou encore Annie Mac, car ce sont des dj's qui organisent leur soirées comme nous ! (mais elles nous connaissent pas encore) 

Votre artiste féminine préférée ?

Beaucoup ! vraiment beaucoup ! Pour en citer quelques unes : Maria Creuza, Gal Gosta, Flora Purim, Alicya Keys, Cecile McLorin Salvant, Sheila Maurice-Grey, Missy Eliott, 

Lady Leshurr, Nubya Garcia, Georgia Anne Muldrow........ y'en a beaucoup troppppp ! 

Une punchline / devise ?

"Nique ton père", non sans blaguer on a utilisé longtemps "des griffes et des bass" mais on vieillit alors on est plutôt "emoji soleil et coeur" comme punchline

Des endroits que vous recommandez pour faire la fête à Marseille ?

Evidemment : Le Cabaret Aléatoire, mille recommandations aussi pour Le Chapiteau La Belle de Mai,  L'Embo & Le Bar Lamifa

Quel est votre spot à apéro ?  

En vrai si je te les donne je ne serais plus jamais incognito ;) 

Le Lonchamp Palace car l'équipe est cool (coucou Yann),  après en réalité ce qui me mets le plus cool pour boire l'apéro c'est de me poser dans les petits bars de quartiers, Marseille en regorge

du plus tordu au plus appétissant :)

Vos prochains évènements ?

Dj Carie et Maureen seront au Rio Loco pour le crew à Toulouse le 14 juin,  Big up au festival avec une prog exclusivement féminine. Et notre date à Marseille le 28 juin : Club Cabaret X Wicked Girls : Mafalda + Bonaventure & more

Que pensez-vous de Support your Local Girl Gang  ? 

On vous suit depuis quelques temps et on sera ravie de vous rencontrer IRL :) Plus on est à travailler dans le même sens et plus on aura de chance de faire bouger les mentalités !

Longue vie à Support Your Local Girl Gang <3

WICKED GIRLS DANS TES RESEAUX : FACEBOOK - WEBSITE

[ferckinclerser]

Alphabet Tag

Rules: Make a new post to answer the alphabet prompts

I was tagged by @rupturedspleen

A: Age: 29

B: Birthday: 13th July (so close to 30 how did this happen i do not know 0o)

C: Current time: 02:31

D: Drink you last had: Lime drink

E: Easiest person to talk to: my partner

F: Favourite song: don’t think i have one, currently listening a lot to dead can dance, alan stivell and tri yann though.

G: Grossest memory: that one time i coughed up a phlegm plug the size of my pinkie

H: Horror, yes or no? depends on the medium, movie no, book no, podcast/audiobook yes.

I: In love with: my partner and ice cream.

J: Jealous of people?: sometimes

K: Killed someone?: ...wtf

L: “love at first sight or should I walk by again?”: worst pick up line?

M: Middle name?: since my middle name is also the name i go by lets just take my 3rd name instead henrietta (yeah i got 3 names, my parents were covering all the family naming traditions, like soooo many names)

N: Number of siblings?: 1 full and 1 half, then 2 ex step

O: One wish?: more energy/executive function

P: Person you last called?: my partner

Q: Questions you’re always asked?: what are you making now? in regards to crafts and things. other than that i don’t know.

R: Reason to smile?: my cats, my partner, packages, new shoes.

S: Song you last sang?: last one i remember while making pizza earlier was weeping song by nick cave 

T: Time you woke up this morning: 14? i think sooooo what is a morning?

U: Underwear colour: stripey black and white

V: Vacation: my planned vacation this summer is gothenburg to see old friends, dream vacation is anywhere i have friends i haven’t met irl before.

W: Worst habit: probably my inability to make new healthy habits 

X: X-ray?: i’ve had a lot of them, mainly due to scoliosis. like 3-5 times a year for 4 years to monitor my growth and then to check the results of my surgery

Y: Your favourite food: spagetti and ketchup is all i need.

Z: Zodiac sign: cancer

I tag: anyone who wants to do it :3 i just feel uncomfortable tagging people (don’t mind being tagged myself tho)

[oihisoka]

tagged by the lovely and talented @b-i-e-r-u 💕

Rules: tag 9 people you’d like to get to know better.

Relationship status: forever alone ;~; (idk if this will continue until forever but i’m learning to love my own company and i also like having a partner so this might change)

Favourite colour: don’t have any favorite color in particular but prefer grey, black, maroon, and emerald green. 

Pets: none but would love to have a cat in the future but i think i might be allergic :-( i went to a cat cafe once and i had a strange rash develop after that ;_;

Last song I listened to: Amelie OST by Yann Tiersen and now my sisters are blasting off BTS - Boy In Luv 

Favourite tv show: 

english based: sherlock holmes, the x-files (will need to get back on this but i dropped it midway due to uni), grey’s anatomy (but dropped it after s10 after Sandra Oh left). i don’t really like watching american/british shows much but i might continue with the x-files.

k-drama: it’s okay that’s love and i’m currently watching reply 1988 and i’m almost done with it. i’m so sad that’s it’s coming to an end because it’s such an excellent show with great plot and characters!! 

anime: hunter x hunter, fma: b, nana, natsume yuujinchou series, haikyuu, yoi, rurouni kenshin, inuyasha, ouran high school host club, skip beat!, kimi ni todoke, chihayafuru, psycho pass, zankyou no terror, kuragehime, and barakamon. each one is very unique and special!

______________________________________________________________________

tagging @iriithyll @oikawaisagenius 

[actutrends]

Generative adversarial networks: What GANs are and how they’ve evolved

Perhaps you’ve read about AI capable of producing humanlike speech or generating images of people that are difficult to distinguish from real-life photographs. More often than not, these systems build upon generative adversarial networks (GANs), which are two-part AI models consisting of a generator that creates samples and a discriminator that attempts to differentiate between the generated samples and real-world samples. This unique arrangement enables GANs to achieve impressive feats of media synthesis, from composing melodies and swapping sheep for giraffes to hallucinating footage of ice skaters and soccer players. In point of fact, it’s because of this prowess that GANs have been used to produce problematic content like deepfakes, which is media that takes a person in existing media and replaces them with someone else’s likeness.

The evolution of GANs — which Facebook AI research director Yann LeCun has called the most interesting idea of the decade — is somewhat long and winding, and very much continues to this day. They have their deficiencies, but GANs remain one of the most versatile neural network architectures in use today.

History of GANs

The idea of pitting two algorithms against each other originated with Arthur Samuel, a prominent researcher in the field of computer science who’s credited with popularized the term “machine learning.” While at IBM, he devised a checkers game — the Samuel Checkers-playing Program — that was among the first to successfully self-learn, in part by estimating the chance of each side’s victory at a given position.

But if Samuel is the grandfather of GANs, Ian Goodfellow, former Google Brain research scientist and director of machine learning at Apple’s Special Projects Group, might be their father. In a seminal 2014 research paper simply titled “Generative Adversarial Nets,” Goodfellow and colleagues describe the first working implementation of a generative model based on adversarial networks.

Goodfellow has often stated that he was inspired by noise-contrastive estimation, a way of learning a data distribution by comparing it against a defined noise distribution (i.e., a mathematical function representing corrupted or distorted data). Noise-contrastive estimation uses the same loss functions as GANs — in other words, the same measure of performance with respect to a model’s ability to anticipate expected outcomes.

Of course, Goodfellow was’t the only one to pursue an adversarial AI model design. Dalle Molle Institute for Artificial Intelligence Research co-director Juergen Schmidhuber advocated predictability minimization, a technique that models distributions through an encoder that maximizes the objective function (the function that specifies the problem to be solved by the system) minimized by a predictor. It adopts what’s known as a minimax decision rule, where the possible loss for a worst case (maximum loss) scenario is minimized as much as possible.

And this is the paradigm upon which GANs are built.

GAN architecture

Again, GANs consist of two parts: generators and discriminators. The generator model produces synthetic examples (e.g., images) from random noise sampled using a distribution, which along with real examples from a training data set are fed to the discriminator, which attempts to distinguish between the two. Both the generator and discriminator improve in their respective abilities until the discriminator is unable to tell the real examples from the synthesized examples with better than the 50% accuracy expected of chance.

GANs train in an unsupervised fashion, meaning that they infer the patterns within data sets without reference to known, labeled, or annotated outcomes. Interestingly, the discriminator’s work informs that of the generator — every time the discriminator correctly identifies a synthesized work, it tells the generator how to tweak its output so that it might be more realistic in the future.

In practice, GANs suffer from a number of shortcomings owing to their architecture. The simultaneous training of generator and discriminator models is inherently unstable. Sometimes the parameters — the configuration values internal to the models — oscillate or destabilize, which isn’t surprising given that after every parameter update, the nature of the optimization problem being solved changes. Alternatively, the generator collapses, and it begins to produce data samples that are largely homogeneous in appearance.

Above: The architecture of a generative adversarial network (GAN).

Image Credit: Google

The generator and discriminator also run the risk of overpowering each other. If the generator becomes too accurate, it’ll exploit weaknesses in the discriminator that lead to undesirable results, whereas if the discriminator becomes too accurate, it’ll impede the generator’s progress toward convergence.

A lack of training data also threatens to impede GANs’ progress in the semantic realm, which in this context refers to the relationships among objects. Today’s best GANs struggle to reconcile the difference between palming and holding an object, for example — a differentiation most humans make in seconds.

But as Hanlin Tang, senior director of Intel’s AI laboratory, explained to VentureBeat in a phone interview, emerging techniques get around these limitations. One entails building multiple discriminator into a model and fine-tuning them on specific data. Another involves feeding discriminator dense embedding representations, or numerical representations of data, so that they have more information from which to draw.

“There [aren’t] that many well-curated data sets to start … applying GANs to,” Tang said. “GANs just follow where the data sets are going.”

On the subject of compute, Youssef Mroueh, a research staff member in the IBM multi-modal algorithms and engines group, is working with colleagues to develop lightweight models dubbed “small GANs” that reduce training time and memory usage. The bulk of their research is concentrated in the MIT-IBM Watson AI Lab, a joint AI research effort between the Massachusetts Institute of Technology and IBM.

“[It’s a] challenging business question: How can we change [the] modeling without all the computation and hassle?” Mroueh said. “That’s what we’re working toward.”

GAN applications

Image and video synthesis

GANs are perhaps best known for their contributions to image synthesis.

StyleGAN, a model Nvidia developed, has generated high-resolution head shots of fictional people by learning attributes like facial pose, freckles, and hair. A newly released version — StyleGAN 2 — makes improvements with respect to both architecture and training methods, redefining the state of the art in terms of perceived quality.

In June 2019, Microsoft researchers detailed ObjGAN, a novel GAN that could understand captions, sketch layouts, and refine the details based on the wording. The coauthors of a related study proposed a system — StoryGAN — that synthesizes storyboards from paragraphs.

Such models have made their way into production. Startup Vue.ai‘s GAN susses out clothing characteristics and learns to produce realistic poses, skin colors, and other features. From snapshots of apparel, it can generate model images in every size up to five times faster than a traditional photo shoot.

Elsewhere, GANs have been applied to the problems of super-resolution (image upsampling) and pose estimation (object transformation). Tang says one of his teams used GANs to train a model to upscale 200-by-200-pixel satellite imagery to 1,000 by 1,000 pixels, and to produce images that appear as though they were captured from alternate angles.

Above: Examples of edits performed by GAN Paint Studio.

Scientists at Carnegie Mellon last year demoed Recycle-GAN, a data-driven approach for transferring the content of one video or photo to another. When trained on footage of human subjects, the GAN generated clips that captured subtle expressions like dimples and lines that formed when subjects smiled and moved their mouths.

More recently, researchers at Seoul-based Hyperconnect published MarioNETte, which synthesizes a reenacted face animated by a person’s movement while preserving the face’s appearance.

On the object synthesis side of the equation, Google and MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) developed a GAN that can generate images of 3D models with realistic lighting and reflections and enables shape and texture editing, as well as viewpoint shifts.

Video

Predicting future events from only a few video frames — a task once considered impossible — is nearly within grasp thanks to state-of-the-art approaches involving GANs and novel data sets.

One of the newest papers on the subject from DeepMind details recent advances in the budding field of AI clip generation. Thanks to “computationally efficient” components and techniques and a new custom-tailored data set, researchers say their best-performing model — Dual Video Discriminator GAN (DVD-GAN) — can generate coherent 256 x 256-pixel videos of “notable fidelity” up to 48 frames in length.

In a twist on the video synthesis formula, Cambridge Consultants last year demoed a model called DeepRay that invents video frames to mitigate distortion caused by rain, dirt, smoke, and other debris.

Artwork

GANs are capable of more than generating images and video footage. When trained on the right data sets, they’re able to produce de novo works of art.

Researchers at the Indian Institute of Technology Hyderabad and the Sri Sathya Sai Institute of Higher Learning devised a GAN, dubbed SkeGAN, that generates stroke-based vector sketches of cats, firetrucks, mosquitoes, and yoga poses.

Scientists at the Maastricht University in the Netherlands created a GAN that produces logos from one of 12 different colors.

Victor Dibia, a human-computer interaction researcher and Carnegie Mellon graduate, trained a GAN to synthesize African tribal masks.

Meanwhile, a team at the University of Edinburgh’s Institute for Perception and Institute for Astronomy designed a model that generates images of fictional galaxies that closely follow the distributions of real galaxies.

In March during its GPU Technology Conference (GTC) in San Jose, California, Nvidia took the wraps off of GauGAN, a generative adversarial AI system that lets users create lifelike landscape images that never existed. GauGAN — whose name comes from post-Impressionist painter Paul Gauguin — improves upon Nvidia’s Pix2PixHD system introduced last year, which was similarly capable of rendering synthetic worlds but left artifacts in its images. The machine learning model underpinning GauGAN was trained on more than one million images from Flickr, imbuing it with an understanding of the relationships among over 180 objects including snow, trees, water, flowers, bushes, hills, and mountains. In practice, trees next to water have reflections, for instance, and the type of precipitation changes depending on the season depicted.

Music

GANs are architecturally well-suited to generating media, and that includes music.

In a paper published in August, researchers hailing from the National Institute of Informatics in Tokyo describe a system that’s able to generate “lyrics-conditioned” melodies from learned relationships between syllables and notes.

Not to be outdone, in December, Amazon Web Services detailed DeepComposer, a cloud-based service that taps a GAN to fill in compositional gaps in songs.

“For a long time, [GANs research] has been about improving the training instabilities whatever the modality is — text, images, sentences, et cetera. Engineering is one thing, but it’s also [about] coming up with [the right] architecture,” said Mroueh. “It’s a combination of lots of things.”

Speech

Google and Imperial College London researchers recently set out to create a GAN-based text-to-speech system capable of matching (or besting) state-of-the-art methods. Their proposed system — GAN-TTS — consists of a neural network that learned to produce raw audio by training on a corpus of speech with 567 pieces of encoded phonetic, duration, and pitch data. To enable the model to generate sentences of arbitrary length, the coauthors sampled 44 hours’ worth of two-second snippets together with the corresponding linguistic features computed for five-millisecond snippets. An ensemble of 10 discriminators — some of which assess linguistic conditioning, while others assess general realism — attempt to distinguish between real and synthetic speech.

Medicine

In the medical field, GANs have been used to produce data on which other AI models — in some cases, other GANs — might train and to invent treatments for rare diseases that to date haven’t received much attention.

In April, the Imperial College London, University of Augsburg, and Technical University of Munich sought to synthesize data to fill in gaps in real data with a model dubbed Snore-GAN. In a similar vein, researchers from Nvidia, the Mayo Clinic, and the MGH and BWH Center for Clinical Data Science proposed a model that generates synthetic magnetic resonance images (MRIs) of brains with cancerous tumors.

https://venturebeat.com/wp-content/uploads/2019/09/abstract.wav

Baltimore-based Insilico Medicine pioneered the use of GANs in molecular structure creation for diseases with a known ligand (a complex biomolecule) but no target (a protein associated with a disease process). Its team of researchers is actively working on drug discovery programs in cancer, dermatological diseases, fibrosis, Parkinson’s, Alzheimer’s, ALS, diabetes, sarcopenia, and aging.

Robotics

The field of robotics has a lot to gain from GANs, as it turns out.

A tuned discriminator can determine whether a machine’s trajectory has been drawn from a distribution of human demonstrations or from synthesized examples. In that way, it’s able to train agents to complete tasks accurately, even when it has access only to the robot’s positional information. (Normally, training robot-directing AI requires both positional and action data. The latter indicates which motors moved over time.)

“The idea of using adversarial loss for training agent trajectories is not new, but what’s new is allowing it to work with a lot less data,” Tang said. “The trick to applying these adversarial learning approaches is figuring out which inputs the discriminator has access to — what information is available to avoid being tricked [by the discriminator] … [In state-of-the-art approaches], discriminators need access to [positional] data alone, allowing us to train with expert demonstrations where all we have are the state data.”

Tang says this enables the training of much more robust models than was previously possible — models that require only about two dozen human demonstrations. “If you reduce the amount of data that the discriminator has access to, you’re reducing the complexity of the data set that you have to provide to the model. These types of adversarial learning methods actually work pretty well in low-data regimes,” he added.

Deepfake detection

GANs’ ability to generate convincing photos and videos of people makes them ripe targets for abuse. Already, malicious actors have used models to generate fake celebrity pornography.

But preliminary research suggests GANs could root out deepfakes just as effectively as they produce them. A paper published on the preprint server Arxiv.org in March describes spamGAN, which learns from a limited corpus of annotated and unannotated data. In experiments, the researchers say that spamGAN outperformed existing spam detection techniques with limited labeled data, achieving accuracy of between 71% and 86% when trained on as little as 10% of labeled data.

Future directions

What might the future hold with respect to GANs? Despite the leaps and bounds brought by this past decade of research, Tang cautions that it’s still early days.

“GANs are still [missing] very fine-grained control,” he said. “[That’s] a big challenge.”

For his part, Mroueh believes that GAN-generated content will become increasingly difficult to distinguish from real content.

“My feeling is that the field will improve,” he said. “Comparing image generation in 2014 to today, I wouldn’t have expected the quality to become that good. If the progress continues like this, [GANs] will remain a very important research project.”

The post Generative adversarial networks: What GANs are and how they’ve evolved appeared first on Actu Trends.