#Neural Networks

[aiweirdness]

They trained an AI model on a widely used knee osteoarthritis dataset to see if it would be able to make nonsensical predictions - whether the patient ate refried beans, or drank beer. It did, in part by somehow figuring out where the x-ray was taken.

The authors point out that AI models base their predictions on sneaky shortcut effects all the time; they're just easier to identify when the conclusions (beer drinking) are clearly spurious.

Algorithmic shortcutting is tough to avoid. Sometimes it's based on something easy to identify - like rulers in images of skin cancer, or sicker patients getting their chest x-rays while lying down.

But as they found here, often it's a subtle mix of non-obvious correlations. They eliminated as many differences between x-ray machines at different sites as they could find, and the model could still tell where the x-ray was taken - and whether the patient drank beer.

AI models are not approaching the problem like a human scientist would - they'll latch onto all sorts of unintended information in an effort to make their predictions.

This is one reason AI models often end up amplifying the racism and gender discrimination in their training data.

When I wrote a book on AI in 2019, it focused on AIs making sneaky shortcuts.

Aside from the vintage generative text (Pumpkin Trash Break ice cream, anyone?), the algorithmic shortcutting is still completely recognizable today.

[gudamor]

My second-favorite

[compneuropapers]

Interesting Papers for Week 3, 2025

Synaptic weight dynamics underlying memory consolidation: Implications for learning rules, circuit organization, and circuit function. Bhasin, B. J., Raymond, J. L., & Goldman, M. S. (2024). Proceedings of the National Academy of Sciences, 121(41), e2406010121.

Characterization of the temporal stability of ToM and pain functional brain networks carry distinct developmental signatures during naturalistic viewing. Bhavna, K., Ghosh, N., Banerjee, R., & Roy, D. (2024). Scientific Reports, 14, 22479.

Connectomic reconstruction predicts visual features used for navigation. Garner, D., Kind, E., Lai, J. Y. H., Nern, A., Zhao, A., Houghton, L., … Kim, S. S. (2024). Nature, 634(8032), 181–190.

Socialization causes long-lasting behavioral changes. Gil-Martí, B., Isidro-Mézcua, J., Poza-Rodriguez, A., Asti Tello, G. S., Treves, G., Turiégano, E., … Martin, F. A. (2024). Scientific Reports, 14, 22302.

Neural pathways and computations that achieve stable contrast processing tuned to natural scenes. Gür, B., Ramirez, L., Cornean, J., Thurn, F., Molina-Obando, S., Ramos-Traslosheros, G., & Silies, M. (2024). Nature Communications, 15, 8580.

Lack of optimistic bias during social evaluation learning reflects reduced positive self-beliefs in depression and social anxiety, but via distinct mechanisms. Hoffmann, J. A., Hobbs, C., Moutoussis, M., & Button, K. S. (2024). Scientific Reports, 14, 22471.

Causal involvement of dorsomedial prefrontal cortex in learning the predictability of observable actions. Kang, P., Moisa, M., Lindström, B., Soutschek, A., Ruff, C. C., & Tobler, P. N. (2024). Nature Communications, 15, 8305.

A transient high-dimensional geometry affords stable conjunctive subspaces for efficient action selection. Kikumoto, A., Bhandari, A., Shibata, K., & Badre, D. (2024). Nature Communications, 15, 8513.

Presaccadic Attention Enhances and Reshapes the Contrast Sensitivity Function Differentially around the Visual Field. Kwak, Y., Zhao, Y., Lu, Z.-L., Hanning, N. M., & Carrasco, M. (2024). eNeuro, 11(9), ENEURO.0243-24.2024.

Transformation of neural coding for vibrotactile stimuli along the ascending somatosensory pathway. Lee, K.-S., Loutit, A. J., de Thomas Wagner, D., Sanders, M., Prsa, M., & Huber, D. (2024). Neuron, 112(19), 3343-3353.e7.

Inhibitory plasticity supports replay generalization in the hippocampus. Liao, Z., Terada, S., Raikov, I. G., Hadjiabadi, D., Szoboszlay, M., Soltesz, I., & Losonczy, A. (2024). Nature Neuroscience, 27(10), 1987–1998.

Third-party punishment-like behavior in a rat model. Mikami, K., Kigami, Y., Doi, T., Choudhury, M. E., Nishikawa, Y., Takahashi, R., … Tanaka, J. (2024). Scientific Reports, 14, 22310.

The morphospace of the brain-cognition organisation. Pacella, V., Nozais, V., Talozzi, L., Abdallah, M., Wassermann, D., Forkel, S. J., & Thiebaut de Schotten, M. (2024). Nature Communications, 15, 8452.

A Drosophila computational brain model reveals sensorimotor processing. Shiu, P. K., Sterne, G. R., Spiller, N., Franconville, R., Sandoval, A., Zhou, J., … Scott, K. (2024). Nature, 634(8032), 210–219.

Decision-making shapes dynamic inter-areal communication within macaque ventral frontal cortex. Stoll, F. M., & Rudebeck, P. H. (2024). Current Biology, 34(19), 4526-4538.e5.

Intrinsic Motivation in Dynamical Control Systems. Tiomkin, S., Nemenman, I., Polani, D., & Tishby, N. (2024). PRX Life, 2(3), 033009.

Coding of self and environment by Pacinian neurons in freely moving animals. Turecek, J., & Ginty, D. D. (2024). Neuron, 112(19), 3267-3277.e6.

The role of training variability for model-based and model-free learning of an arbitrary visuomotor mapping. Velázquez-Vargas, C. A., Daw, N. D., & Taylor, J. A. (2024). PLOS Computational Biology, 20(9), e1012471.

Rejecting unfairness enhances the implicit sense of agency in the human brain. Wang, Y., & Zhou, J. (2024). Scientific Reports, 14, 22822.

Impaired motor-to-sensory transformation mediates auditory hallucinations. Yang, F., Zhu, H., Cao, X., Li, H., Fang, X., Yu, L., … Tian, X. (2024). PLOS Biology, 22(10), e3002836.

[margocooper]

Поздравляю всех с праздником любви и нежности, с Днем святого Валентина! Пусть любовь всегда будет чиста, верна и преданна. Пусть ваши половинки будет всегда рядом, оберегают от всех невзгод и неурядиц. Пусть ваши чувства будут теплыми и крепкими, страстными и взаимными.

Congratulations to everyone on the holiday of love and tenderness, Happy Valentine's Day! May love always be pure, faithful and devoted. Let your other halves always be there, protect you from all adversity and troubles. Let your feelings be warm and strong, passionate and mutual.

Source: poems taken from the Internet.

[multibodied]

9 times of 10 I see AI hate it is misaddressed from the actual problem, which isn't the fucking learning algorithms but the capitalistic desire to squeeze as much money with as little effort as possible from everything and anything that promises a prospect of Any financial gain and prioritises it over quality and whether it actually makes someone's life better, because the measure of "value" is entirely linked to financial gain. It doesn't matter if it makes our world a better place, it doesn't matter whether it makes our world a significantly worse place, what matters is whether it sells. And THIS is the problem.

AI voice assistants, chats and other machine learning tools are not the enemy to hate on. The system surrounding their use that prioritises the interests of CEOs over the interests of general public as well as Requires people to do stupid useless things for money to survive is the actual problem. Ironically, the people who could benefit from AI tools the most, those whose life could literally be turned around for the better (people with various disabilities) are the LAST people who are considered in this ai race. Because the system dictates that it'll rather focus on cheap production of shitty pictures to cut costs and eliminate the need for the rich to pay those of us who may actually enjoy their job rather than make accessibility tools actually accessible, despite being able to do so if only it was the priority.

We have chatbots who speak in natural voices, we have face and object recognition features integrated into our phones. But we don't have screen-readers that don't suck, we don't have accessible tools for translating in real time what the camera sees into accurate descriptions to help visually impaired people. We have algorithms to generate pictures, social medias integrate various bots to put them on their platforms for god knows why, but what they don't have is algorithms that could automatically generate text descriptions of pictures and videos posted on them. What they don't have is AI tools for detecting flashing in videos and gifs and a way to filter them. They have algorithms searching for porn and copyrighted materials tho even if it's just a few seconds of music created by a world famous artist who has been dead for decades.

Granted, we have really good automated subtitles and translators, but at the same time there are no automated descriptions of other sounds while the tools for GENERATING various sounds exist. And subtitles themselves do nothing to convey intonation even though just adding some cursive words when a speaker makes an emphasis on them would already greatly improve the experience.

Whenever I think of the current state of AI, I remember that project that through implants gave blind people the ability to see. The one that got shut down and left all the people who used it blind again. Because it wasn't profitable.

[x-heesy]

ᗯE ᑎEEᗪ ᗰᗩGIᑕK

Vɪsʜᴍᴀ Mᴀʜᴀʀᴀᴊ ᴀᴋᴀ ᴀʀᴛɪsᴛɪᴄ_ɪᴍᴀɢɪɴɪɴɢs 🎭

Iɴᴄʀᴇᴅɪʙʟᴇ ғᴀɴᴛᴀsʏ ᴅʀᴇssᴇs ғʀᴏᴍ ᴀ ɴᴇᴜʀᴀʟ ɴᴇᴛᴡᴏʀᴋ.

#aiart #art #ai #digitalart #generativeart #artificialintelligence #machinelearning #aiartcommunity #abstractart #nft #aiartists #neuralart #vqgan #ganart #contemporaryart #deepdream #artist #nftart #artoftheday #newmediaart #nightcafestudio #aiartist #modernart #neuralnetworks #neuralnetworkart #abstract #styletransfer #stylegan #digitalartist #artbreeder

Fᴀʙʟᴇs & Fᴀɪʀʏᴛᴀʟᴇs - Dᴇɴɪᴢ Kᴜʀᴛᴇʟ Rᴇᴍɪx ʙʏ N/ᴀ, Rᴏsɪɴᴀ 🎧 🧚‍♀️

[nikjag]

simulation of schizophrenia

so i built a simulation of schizophrenia using rust and python

basically you have two groups of simulated neurons, one inhibitory and one excitatory. the excitatory group is connected so they will settle on one specific pattern. the inhibitory group is connected to the excitatory group semi-randomly. the excitatory group releases glutamate while the inhibitory group releases gaba. glutamate will cause the neurons to increase in voltage (or depolarize), gaba will cause the neurons to decrease in voltage (hyperpolarize).

heres a quick visualization of the results in manim

the y axis represents the average firing rate of the excitatory group over time, decay refers to how quickly glutamate is cleared from the neuronal synapse. there are two versions of the simulation, one where the excitatory group is presented with a cue, and one where it is not presented with a cue. when the cue is present, the excitatory group remembers the pattern and settles on it, represented by an increased firing rate. however, not every trial in the simulation leads to a memory recall, if the glutamate clearance happens too quickly, the memory is not maintained. on the other hand, when no cue is presented if glutamate clearance is too low, spontaneous activity overcomes inhibition and activity persists despite there being no input, ie a hallucination.

the simulation demonstrates the failure to maintain the state of the network, either failing to maintain the prescence of a cue or failing to maintain the absence of a cue. this is thought to be one possible explaination of certain schizophrenic symptoms from a computational neuroscience perspective

[ai-innova7ions]

Neturbiz Enterprises - AI Innov7ions

Our mission is to provide details about AI-powered platforms across different technologies, each of which offer unique set of features. The AI industry encompasses a broad range of technologies designed to simulate human intelligence. These include machine learning, natural language processing, robotics, computer vision, and more. Companies and research institutions are continuously advancing AI capabilities, from creating sophisticated algorithms to developing powerful hardware. The AI industry, characterized by the development and deployment of artificial intelligence technologies, has a profound impact on our daily lives, reshaping various aspects of how we live, work, and interact.

[dzamie]

Detecting AI-generated research papers through "tortured phrases"

So, a recent paper found and discusses a new way to figure out if a "research paper" is, in fact, phony AI-generated nonsense. How, you may ask? The same way teachers and professors detect if you just copied your paper from online and threw a thesaurus at it!

It looks for “tortured phrases”; that is, phrases which resemble standard field-specific jargon, but seemingly mangled by a thesaurus. Here's some examples (transcript below the cut):

profound neural organization - deep neural network

(fake | counterfeit) neural organization - artificial neural network

versatile organization - mobile network

organization (ambush | assault) - network attack

organization association - network connection

(enormous | huge | immense | colossal) information - big data

information (stockroom | distribution center) - data warehouse

(counterfeit | human-made) consciousness - artificial intelligence (AI)

elite figuring - high performance computing

haze figuring - fog/mist/cloud computing

designs preparing unit - graphics processing unit (GPU)

focal preparing unit - central processing unit (CPU)

work process motor - workflow engine

facial acknowledgement - face recognition

discourse acknowledgement - voice recognition

mean square (mistake | blunder) - mean square error

mean (outright | supreme) (mistake | blunder) - mean absolute error

(motion | flag | indicator | sign | signal) to (clamor | commotion | noise) - signal to noise

worldwide parameters - global parameters

(arbitrary | irregular) get right of passage to - random access

(arbitrary | irregular) (backwoods | timberland | lush territory) - random forest

(arbitrary | irregular) esteem - random value

subterranean insect (state | province | area | region | settlement) - ant colony

underground creepy crawly (state | province | area | region | settlement) - ant colony

leftover vitality - remaining energy

territorial normal vitality - local average energy

motor vitality - kinetic energy

(credulous | innocent | gullible) Bayes - naïve Bayes

individual computerized collaborator - personal digital assistant (PDA)

[aiweirdness]

Nobody should be using GPT detectors for anything important.

This is from a recent study that found that GPT detectors were misclassifying writing by non-native English speakers as AI-generated 48-76% of the time (!!!), compared to 0%-12% for native speakers.

It is irresponsible to use AI-generated text detectors as evidence of academic misconduct, and that's putting it mildly.

[asyaakri]

I love you as certain dark things are to be loved, in secret, between the shadow and the soul.

PABLO NERUDA

One Hundred Love Sonnets: XVII

[materialsscienceandengineering]

Fiber image transmission technology for minimally invasive endoscope developed

Optical fibers are fundamental components in modern science and technology due to their inherent advantages, providing an efficient and secure medium for applications such as internet communication and big data transmission. Compared with single-mode fibers (SMFs), multimode fibers (MMFs) can support a much larger number of guided modes (~103 to ~104), offering the attractive advantage of high-capacity information and image transportation within the diameter of a hair. This capability has positioned MMFs as a critical tool in fields such as quantum information and micro-endoscopy. However, MMFs pose a significant challenge: their highly scattering nature introduces severe modal dispersion during transmission, which significantly degrades the quality of transmitted information. Existing technologies, such as artificial neural networks (ANNs) and spatial light modulators (SLMs), have achieved limited success in reconstructing distorted images after MMF transmission. Despite these advancements, the direct optical transmission of undistorted images through MMFs using micron-scale integrated optical components has remained an elusive goal in optical research.

Read more.

[compneuropapers]

Interesting Papers for Week 10, 2025

Simplified internal models in human control of complex objects. Bazzi, S., Stansfield, S., Hogan, N., & Sternad, D. (2024). PLOS Computational Biology, 20(11), e1012599.

Co-contraction embodies uncertainty: An optimal feedforward strategy for robust motor control. Berret, B., Verdel, D., Burdet, E., & Jean, F. (2024). PLOS Computational Biology, 20(11), e1012598.

Distributed representations of behaviour-derived object dimensions in the human visual system. Contier, O., Baker, C. I., & Hebart, M. N. (2024). Nature Human Behaviour, 8(11), 2179–2193.

Thalamic spindles and Up states coordinate cortical and hippocampal co-ripples in humans. Dickey, C. W., Verzhbinsky, I. A., Kajfez, S., Rosen, B. Q., Gonzalez, C. E., Chauvel, P. Y., Cash, S. S., Pati, S., & Halgren, E. (2024). PLOS Biology, 22(11), e3002855.

Preconfigured cortico-thalamic neural dynamics constrain movement-associated thalamic activity. González-Pereyra, P., Sánchez-Lobato, O., Martínez-Montalvo, M. G., Ortega-Romero, D. I., Pérez-Díaz, C. I., Merchant, H., Tellez, L. A., & Rueda-Orozco, P. E. (2024). Nature Communications, 15, 10185.

A tradeoff between efficiency and robustness in the hippocampal-neocortical memory network during human and rodent sleep. Hahn, M. A., Lendner, J. D., Anwander, M., Slama, K. S. J., Knight, R. T., Lin, J. J., & Helfrich, R. F. (2024). Progress in Neurobiology, 242, 102672.

NREM sleep improves behavioral performance by desynchronizing cortical circuits. Kharas, N., Chelaru, M. I., Eagleman, S., Parajuli, A., & Dragoi, V. (2024). Science, 386(6724), 892–897.

Human hippocampus and dorsomedial prefrontal cortex infer and update latent causes during social interaction. Mahmoodi, A., Luo, S., Harbison, C., Piray, P., & Rushworth, M. F. S. (2024). Neuron, 112(22), 3796-3809.e9.

Can compression take place in working memory without a central contribution of long-term memory? Mathy, F., Friedman, O., & Gauvrit, N. (2024). Memory & Cognition, 52(8), 1726–1736.

Offline hippocampal reactivation during dentate spikes supports flexible memory. McHugh, S. B., Lopes-dos-Santos, V., Castelli, M., Gava, G. P., Thompson, S. E., Tam, S. K. E., Hartwich, K., Perry, B., Toth, R., Denison, T., Sharott, A., & Dupret, D. (2024). Neuron, 112(22), 3768-3781.e8.

Reward Bases: A simple mechanism for adaptive acquisition of multiple reward types. Millidge, B., Song, Y., Lak, A., Walton, M. E., & Bogacz, R. (2024). PLOS Computational Biology, 20(11), e1012580.

Hidden state inference requires abstract contextual representations in the ventral hippocampus. Mishchanchuk, K., Gregoriou, G., Qü, A., Kastler, A., Huys, Q. J. M., Wilbrecht, L., & MacAskill, A. F. (2024). Science, 386(6724), 926–932.

Dopamine builds and reveals reward-associated latent behavioral attractors. Naudé, J., Sarazin, M. X. B., Mondoloni, S., Hannesse, B., Vicq, E., Amegandjin, F., Mourot, A., Faure, P., & Delord, B. (2024). Nature Communications, 15, 9825.

Compensation to visual impairments and behavioral plasticity in navigating ants. Schwarz, S., Clement, L., Haalck, L., Risse, B., & Wystrach, A. (2024). Proceedings of the National Academy of Sciences, 121(48), e2410908121.

Replay shapes abstract cognitive maps for efficient social navigation. Son, J.-Y., Vives, M.-L., Bhandari, A., & FeldmanHall, O. (2024). Nature Human Behaviour, 8(11), 2156–2167.

Rapid modulation of striatal cholinergic interneurons and dopamine release by satellite astrocytes. Stedehouder, J., Roberts, B. M., Raina, S., Bossi, S., Liu, A. K. L., Doig, N. M., McGerty, K., Magill, P. J., Parkkinen, L., & Cragg, S. J. (2024). Nature Communications, 15, 10017.

A hierarchical active inference model of spatial alternation tasks and the hippocampal-prefrontal circuit. Van de Maele, T., Dhoedt, B., Verbelen, T., & Pezzulo, G. (2024). Nature Communications, 15, 9892.

Cognitive reserve against Alzheimer’s pathology is linked to brain activity during memory formation. Vockert, N., Machts, J., Kleineidam, L., Nemali, A., Incesoy, E. I., Bernal, J., Schütze, H., Yakupov, R., Peters, O., Gref, D., Schneider, L. S., Preis, L., Priller, J., Spruth, E. J., Altenstein, S., Schneider, A., Fliessbach, K., Wiltfang, J., Rostamzadeh, A., … Ziegler, G. (2024). Nature Communications, 15, 9815.

The human posterior parietal cortices orthogonalize the representation of different streams of information concurrently coded in visual working memory. Xu, Y. (2024). PLOS Biology, 22(11), e3002915.

Challenging the Bayesian confidence hypothesis in perceptual decision-making. Xue, K., Shekhar, M., & Rahnev, D. (2024). Proceedings of the National Academy of Sciences, 121(48), e2410487121.

[bphnx]

Hela

Ultron

Mysterio

Venom

Doctor Doom

Red Skull

Green Goblin

Model: Dreamshaper XL 1.0