#IEEE Transactions on Robotics | Explore Tumblr posts and blogs

drmikewatts · 10 days ago

Text

IEEE Transactions on Cognitive and Developmental Systems, Volume 17, Issue 3, June 2025

1) Enhancing Dimensional Image Emotion Detection With a Low-Resource Dataset via Two-Stage Training

Author(s): SangEun Lee, Seoyun Kim, Yubeen Lee, Jufeng Yang, Eunil Park

Pages: 455 - 464

2) HDMTK: Full Integration of Hierarchical Decision-Making and Tactical Knowledge in Multiagent Adversarial Games

Author(s): Wei Li, Boling Hu, Aiguo Song, Kaizhu Huang

Pages: 465 - 479

3) Functional Connectivity Patterns Learning for EEG-Based Emotion Recognition

Author(s): Chongxing Shi, C. L. Philip Chen, Shuzhen Li, Tong Zhang

Pages: 480 - 494

4) PDRL: Towards Deeper States and Further Behaviors in Unsupervised Skill Discovery by Progressive Diversity

Author(s): Ziming He, Chao Song, Jingchen Li, Haobin Shi

Pages: 495 - 509

5) Simultaneous Estimation of Human Motion Intention and Time-Varying Arm Stiffness for Enhanced Human–Robot Interaction

Author(s): Huayang Wu, Chengzhi Zhu, Long Cheng, Chenguang Yang, Yanan Li

Pages: 510 - 524

6) A Task-Oriented Deep Learning Approach for Human Localization

Author(s): Yu-Jia Chen, Wei Chen, Sai Qian Zhang, Hai-Yan Huang, H.T. Kung

Pages: 525 - 539

7) Adaptive Environment Generation for Continual Learning: Integrating Constraint Logic Programming With Deep Reinforcement Learning

Author(s): Youness Boutyour, Abdellah Idrissi

Pages: 540 - 553

8) Kernel-Based Actor–Critic Learning Framework for Autonomous Brain Control on Trajectory

Author(s): Zhiwei Song, Xiang Zhang, Shuhang Chen, Jieyuan Tan, Yiwen Wang

Pages: 554 - 563

9) Task and Motion Planning of Service Robot Arm in Unknown Environment Based on Virtual Voxel-Semantic Space

Author(s): Lipeng Wang, Xiaochen Wang, Junjun Huang, Mengjie Liu

Pages: 564 - 576

10) Data Augmentation for Seizure Prediction With Generative Diffusion Model

Author(s): Kai Shu, Le Wu, Yuchang Zhao, Aiping Liu, Ruobing Qian, Xun Chen

Pages: 577 - 591

11) Developmental Networks With Foveation

Author(s): Xiang Wu, Juyang Weng

Pages: 592 - 605

12) Modeling Task Engagement to Regulate Reinforcement Learning-Based Decoding for Online Brain Control

Author(s): Xiang Zhang, Xiang Shen, Yiwen Wang

Pages: 606 - 614

13) SMART: Sequential Multiagent Reinforcement Learning With Role Assignment Using Transformer

Author(s): Yixing Lan, Hao Gao, Xin Xu, Qiang Fang, Yujun Zeng

Pages: 615 - 630

14) Interaction Is Worth More Explanations: Improving Human–Object Interaction Representation With Propositional Knowledge

Author(s): Feng Yang, Yichao Cao, Xuanpeng Li, Weigong Zhang

Pages: 631 - 643

15) Spatial–Temporal Spiking Feature Pruning in Spiking Transformer

Author(s): Zhaokun Zhou, Kaiwei Che, Jun Niu, Man Yao, Guoqi Li, Li Yuan, Guibo Luo, Yuesheng Zhu

Pages: 644 - 658

16) A Biomathematical Model for Classifying Sleep Stages Using Deep Learning Techniques

Author(s): Ruijie He, Wei Tong, Miaomiao Zhang, Guangyu Zhu, Edmond Q. Wu

Pages: 659 - 671

17) The Effect of Audio Trigger’s Frequency on Autonomous Sensory Meridian Response

Author(s): Lili Li, Zhiqing Wu, Zhongliang Yu, Zhibin He, Zhizhong Wang, Liyu Lin, Shaolong Kuang

Pages: 672 - 681

18) Location-Guided Head Pose Estimation for Fisheye Image

Author(s): Bing Li, Dong Zhang, Cheng Huang, Yun Xian, Ming Li, Dah-Jye Lee

Pages: 682 - 697

19) Brain Network Reorganization in Response to Multilevel Mental Workload in Simulated Flight Tasks

Author(s): Kuijun Wu, Jingjia Yuan, Xianliang Ge, Ioannis Kakkos, Linze Qian, Sujie Wang, Yamei Yu, Chuantao Li, Yu Sun

Pages: 698 - 709

#ai #artificial intelligence

0 notes

sunaleisocial · 5 months ago

Text

MIT engineers help multirobot systems stay in the safety zone

New Post has been published on https://sunalei.org/news/mit-engineers-help-multirobot-systems-stay-in-the-safety-zone/

MIT engineers help multirobot systems stay in the safety zone

Drone shows are an increasingly popular form of large-scale light display. These shows incorporate hundreds to thousands of airborne bots, each programmed to fly in paths that together form intricate shapes and patterns across the sky. When they go as planned, drone shows can be spectacular. But when one or more drones malfunction, as has happened recently in Florida, New York, and elsewhere, they can be a serious hazard to spectators on the ground.

Drone show accidents highlight the challenges of maintaining safety in what engineers call “multiagent systems” — systems of multiple coordinated, collaborative, and computer-programmed agents, such as robots, drones, and self-driving cars.

Now, a team of MIT engineers has developed a training method for multiagent systems that can guarantee their safe operation in crowded environments. The researchers found that once the method is used to train a small number of agents, the safety margins and controls learned by those agents can automatically scale to any larger number of agents, in a way that ensures the safety of the system as a whole.

In real-world demonstrations, the team trained a small number of palm-sized drones to safely carry out different objectives, from simultaneously switching positions midflight to landing on designated moving vehicles on the ground. In simulations, the researchers showed that the same programs, trained on a few drones, could be copied and scaled up to thousands of drones, enabling a large system of agents to safely accomplish the same tasks.

A team of Crazyflie drones use MIT algorithm to safely switch positions while avoiding obstacles

Image: Courtesy of the researchers

Previous item Next item

“This could be a standard for any application that requires a team of agents, such as warehouse robots, search-and-rescue drones, and self-driving cars,” says Chuchu Fan, associate professor of aeronautics and astronautics at MIT. “This provides a shield, or safety filter, saying each agent can continue with their mission, and we’ll tell you how to be safe.”

Fan and her colleagues report on their new method in a study appearing this month in the journal IEEE Transactions on Robotics. The study’s co-authors are MIT graduate students Songyuan Zhang and Oswin So as well as former MIT postdoc Kunal Garg, who is now an assistant professor at Arizona State University.

Mall margins

When engineers design for safety in any multiagent system, they typically have to consider the potential paths of every single agent with respect to every other agent in the system. This pair-wise path-planning is a time-consuming and computationally expensive process. And even then, safety is not guaranteed.

“In a drone show, each drone is given a specific trajectory — a set of waypoints and a set of times — and then they essentially close their eyes and follow the plan,” says Zhang, the study’s lead author. “Since they only know where they have to be and at what time, if there are unexpected things that happen, they don’t know how to adapt.”

The MIT team looked instead to develop a method to train a small number of agents to maneuver safely, in a way that could efficiently scale to any number of agents in the system. And, rather than plan specific paths for individual agents, the method would enable agents to continually map their safety margins, or boundaries beyond which they might be unsafe. An agent could then take any number of paths to accomplish its task, as long as it stays within its safety margins.

In some sense, the team says the method is similar to how humans intuitively navigate their surroundings.

“Say you’re in a really crowded shopping mall,” So explains. “You don’t care about anyone beyond the people who are in your immediate neighborhood, like the 5 meters surrounding you, in terms of getting around safely and not bumping into anyone. Our work takes a similar local approach.”

Safety barrier

In their new study, the team presents their method, GCBF+, which stands for “Graph Control Barrier Function.” A barrier function is a mathematical term used in robotics that calculates a sort of safety barrier, or a boundary beyond which an agent has a high probability of being unsafe. For any given agent, this safety zone can change moment to moment, as the agent moves among other agents that are themselves moving within the system.

When designers calculate barrier functions for any one agent in a multiagent system, they typically have to take into account the potential paths and interactions with every other agent in the system. Instead, the MIT team’s method calculates the safety zones of just a handful of agents, in a way that is accurate enough to represent the dynamics of many more agents in the system.

“Then we can sort of copy-paste this barrier function for every single agent, and then suddenly we have a graph of safety zones that works for any number of agents in the system,” So says.

To calculate an agent’s barrier function, the team’s method first takes into account an agent’s “sensing radius,” or how much of the surroundings an agent can observe, depending on its sensor capabilities. Just as in the shopping mall analogy, the researchers assume that the agent only cares about the agents that are within its sensing radius, in terms of keeping safe and avoiding collisions with those agents.

Then, using computer models that capture an agent’s particular mechanical capabilities and limits, the team simulates a “controller,” or a set of instructions for how the agent and a handful of similar agents should move around. They then run simulations of multiple agents moving along certain trajectories, and record whether and how they collide or otherwise interact.

“Once we have these trajectories, we can compute some laws that we want to minimize, like say, how many safety violations we have in the current controller,” Zhang says. “Then we update the controller to be safer.”

In this way, a controller can be programmed into actual agents, which would enable them to continually map their safety zone based on any other agents they can sense in their immediate surroundings, and then move within that safety zone to accomplish their task.

“Our controller is reactive,” Fan says. “We don’t preplan a path beforehand. Our controller is constantly taking in information about where an agent is going, what is its velocity, how fast other drones are going. It’s using all this information to come up with a plan on the fly and it’s replanning every time. So, if the situation changes, it’s always able to adapt to stay safe.”

The team demonstrated GCBF+ on a system of eight Crazyflies — lightweight, palm-sized quadrotor drones that they tasked with flying and switching positions in midair. If the drones were to do so by taking the straightest path, they would surely collide. But after training with the team’s method, the drones were able to make real-time adjustments to maneuver around each other, keeping within their respective safety zones, to successfully switch positions on the fly.

In similar fashion, the team tasked the drones with flying around, then landing on specific Turtlebots — wheeled robots with shell-like tops. The Turtlebots drove continuously around in a large circle, and the Crazyflies were able to avoid colliding with each other as they made their landings.

“Using our framework, we only need to give the drones their destinations instead of the whole collision-free trajectory, and the drones can figure out how to arrive at their destinations without collision themselves,” says Fan, who envisions the method could be applied to any multiagent system to guarantee its safety, including collision avoidance systems in drone shows, warehouse robots, autonomous driving vehicles, and drone delivery systems.

This work was partly supported by the U.S. National Science Foundation, MIT Lincoln Laboratory under the Safety in Aerobatic Flight Regimes (SAFR) program, and the Defence Science and Technology Agency of Singapore.

0 notes

journals212 · 2 years ago

Text

Exploring the Top Engineering Journals for Cutting-Edge Research

Introduction:

Engineering is a dynamic field that drives innovation and technological advancements across various industries. Keeping up with the latest research and developments is essential for engineers and researchers alike. This article presents a curated list of some of the best engineering journals that publish high-quality research, covering a range of disciplines within the field.

1. IEEE Transactions on Engineering Management:

This journal focuses on research related to management and leadership in engineering and technology organizations. It covers areas such as project management, innovation, technology assessment, and organizational behavior.

2. Journal of Mechanical Engineering Science:

Published by the Institution of Mechanical Engineers, this journal features research in mechanical engineering and related areas like materials science, fluid dynamics, and thermodynamics.

3. Journal of Structural Engineering:

As the name suggests, this journal concentrates on structural engineering, covering topics such as structural analysis, design, construction, and maintenance.

4. Environmental Science & Technology:

This interdisciplinary journal includes research related to environmental best engineering journals, pollution control, waste management, and sustainable technologies.

5. IEEE Transactions on Neural Networks and Learning Systems:

For those interested in the intersection of best engineering journals and artificial intelligence, this journal explores neural networks, machine learning, and computational intelligence applications.

6. Journal of Biomedical Engineering:

Focusing on the interface of engineering and biology, this journal publishes research on medical device development, biomechanics, and medical imaging.

7. Computer-Aided Civil and Infrastructure Engineering:

This journal covers computational methods and software tools in civil engineering, aiding in the design, analysis, and construction of infrastructure projects.

8. IEEE Transactions on Automation Science and Engineering:

With a focus on automation, this journal explores topics like robotics, control systems, automation technologies, and their applications.

9. Chemical Engineering Journal:

This journal is dedicated to research in chemical engineering, including process design, chemical reaction engineering, and separation processes.

10. International Journal of Electrical Power & Energy Systems:

Covering electrical power generation, transmission, distribution, and utilization, this journal is essential for electrical engineers working in the energy sector.

Conclusion:

Staying informed about the latest advancements in best engineering journals is crucial for professionals and researchers in the field. The aforementioned journals represent just a selection of the many excellent resources available for accessing cutting-edge research and insights in engineering disciplines. Depending on your specific interests, you can explore these journals to deepen your knowledge and contribute to the advancement of engineering and technology.

Hyderabad

Telangana

#research papers #publish journal

0 notes

voidkunal · 5 years ago

Text

Another Research Paper Published on "Study & Analysis of Frequency Reuse for Massive MIMO System".

#ieee #ieeeprojects #ieee transactions on robotics #electronicsandcommunicationengineering #electronics #electronics and communication #electronic #paper #published #publishing

1 note · View note

vsplusonline · 5 years ago

Text

https://timesofindia.indiatimes.com/

New Post has been published on https://apzweb.com/https-timesofindia-indiatimes-com-15/

https://timesofindia.indiatimes.com/

WASHINGTON: Researchers have developed a novel algorithm that may allow collision-free transportation in autonomous vehicles, an advance which they claim can help self-driving cars navigate each other without crashing, or causing traffic jams.

The study, published in the journal IEEE Transactions on Robotics, tested the algorithm in a simulation of 1,024 robots, and on a swarm of 100 real robots, and reported that the bots reliably, safely, and efficiently converged to form a pre-determined shape in less than a minute.

“If you have many autonomous vehicles on the road, you don’t want them to collide with one another or get stuck in a deadlock,” said Michael Rubenstein, study lead author from Northwestern University in the US.

“By understanding how to control our swarm robots to form shapes, we can understand how to control fleets of autonomous vehicles as they interact with each other,” Rubenstein said.

According to the researchers, the advantage of a swarm of small robots- versus one large robot, or a collective of bots with one lead- is the lack of a centralised control.

The new algorithm, the scientists said, allows for decentralised swarms, and acts as a fail-safe, the study noted.

“If the system is centralized and a robot stops working, then the entire system fails. In a decentralized system, there is no leader telling all the other robots what to do. Each robot makes its own decisions,” Rubenstein explained.

“If one robot fails in a swarm, the swarm can still accomplish the task,” he added.

The researchers said the robots need to coordinate in order to avoid collisions, and for achieving this, the algorithm views the ground beneath the robots as a grid.

Using technology that is similar to the Global Positioning System (GPS) which enables location tracking in mobile phones, each robot is aware of where it sits on the grid, the study noted.

In this set up, the scientists said, individual robots use sensors to communicate with their neighbours before making a decision about where to move.

The robots then determine whether or not nearby spaces within the grid are vacant or occupied, they explained.

“The robots refuse to move to a spot until that spot is free, and until they know that no other robots are moving to that same spot. They are careful and reserve a space ahead of time,” Rubenstein said.

The robots then communicate and move swiftly to form a shape, the study noted.

According to Rubenstein, this is achieved by keeping the robots near-sighted.

“Each robot can only sense three or four of its closest neighbours. They can’t see across the whole swarm, which makes it easier to scale the system,” the Northwestern University scientist explained.

“The robots interact locally to make decisions without global information,” he added.

In the swarm engineered by the researchers, 100 robots can coordinate to form a shape within a minute, the study noted.

In earlier approaches, this could take a full hour, they said.

“Large companies have warehouses with hundreds of robots doing tasks similar to what our robots do in the lab,” Rubenstein said.

“They need to make sure their robots don’t collide but do move as quickly as possible to reach the spot where they eventually give an object to a human,” he added.

Source link

#IEEE Transactions on Robotics #Michael Rubenstein #Northwestern University #self-driving cars #self-driving cars algorithm #Technology

0 notes

dihalect · 3 years ago

Text

actually heres the reading list for the artificial life class i mentioned in the tags a couple posts ago. if anyone wants a pdf of one/some of these and can't find it elsewhere, just hmu

(and if you're interested in this sort of thing, i also recommend taking a look at other papers in these publications, including other issues/years)

David Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989

John R Koza, INTRODUCTION TO GENETIC PROGRAMMING TUTORIAL GECCO-2004—SEATTLE

Joel Schiff: Cellular Automata, A discrete view of the world (2008) Addison Wesley.

Stephen Wolfram, Cellular Automata, Los Alamos Science, Fall 1983

Christopher Langton, Self-Reproduction in Cellular Automata, Physica 10D (1984) 135-144

Thomas Ray, An approach to the synthesis of life (1991) Artificial Life II

Richard Lenski et al (2003) The evolutionary origin of complex features. Nature 423 8 May 2003

John Maynard-Smith (1982) Evolution and the Theory of Games, Cambridge Univ Press

Robert Axelrod (1980) Effective Choice in the Prisoner’s Dilemma, The Journal of Conflict Resolution Vol. 24, No. 1, Mar., 1980

Kristian Lindgren, 1992, Evolutionary Phenomena in Simple Dynamics, Artificial Life II and Nick Moran (2019) Appendix A of PhD Dissertation

P Prusinkiewicz et al. 1995 The Artificial Life of Plants, Siggraph 95 Tutorial

Gabriela Ochoa 1998 On genetic algorithms and lindenmayer systems, PPSN V.

Peter Angeline et al (1994) An evolutionary algorithm that constructs recurrent neural networks, IEEE Transactions on Neural Networks

Ken Stanley & Risto Miikkulainen (2002) Evolving neural networks throught augmenting topologies, Evolutionary Computation 10(2)99-127.

Frederic Gruau, 1993, Genetic synthesis of modular neural networks, ICGA 93

Richard Dawkins, 1986, The Blind Watchmaker, Norton.

Jimmy Secretan et al (2010) Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space, Evolutionary Computation

Jeff Clune and Hod Lipson, Evolving Three-Dimensional Objects with a Generative Encoding Inspired by Developmental Biology (2011) ECAL

Danny Hillis, Coevolving Parasites Improves Simulated Evolution as an optimization Procedure, 1990, Physica D 42, 228-234.

H. Juille and J. Pollack (1998) Coevolutionary Learning: A case study. Proceedings of the Fifteenth International Conference on Machine Learning.

Watson, R.A. and Pollack, J.B. (2001). Coevolutionary Dynamics in a Minimal Substrate. Proceedings of the 2001 Genetic and Evolutionary Computation Conference.

Karl Sims, "Evolving 3D Morphology and Behavior by Competition" Artificial Life IV Proceedings, ed.by Brooks & Maes, MIT Press, 1994, pp.28-39.

Pollack, Jordan. B., Lipson, Hod, Hornby, Gregory S. and Funes, Pablo (2001). Three Generations of Automatically Designed Robots. Artificial Life, 7:3.

#txt #save #tech stuff

2 notes · View notes

nikosxanthos · 5 years ago

Text

Bicentennial Man

Η ταινία “Bicentennial Man” γυρίστηκε το 1999 με σκηνοθέτη τον Chris Columbus και είναι βασισμένη στο μυθιστόρημα “The Positronic Man”. Μιλάει για τη ζωή ενός ανθρωποειδούς ρομπότ, ονόματι Andrew, που κατάφερε να γίνει εξ’ ολοκλήρου άνθρωπος. Η αρχή της ταινίας λαμβάνει μέρος το 2005 και τελειώνει με το τέλος της ζωής του Andrew το 2205.

Η ιστορία ξεκινάει με μία οικογένεια που αγοράζει ένα ρομπότ, το οποίο είναι προγραμματισμένο να υπακούει στις εντολές των ανθρώπων. Ένα από τα πρώτα πράγματα που βλέπουμε να κάνει το ρομπότ, είναι να εμφανίζει ένα ολόγραμμα μπροστά στην οικογένεια. Στη συνέχεια, στην ταινία φαίνεται πως ο Andrew είναι διαφορετικός από τα άλλα ρομπότ. Βέβαια, αυτό δεν είναι παρά το αποτέλεσμα ενός τεχνικού λάθους, το οποίο ωστόσο δίνει τη δυνατότητα στο ρομπότ μας να έχει ανθρώπινη συμπεριφορά ως προς τον χαρακτήρα και την προσωπικότητά του. Παρατηρούμε, δηλαδή, πως ο Andrew έχει λογική και συναισθήματα, δείχνει σημάδια δημιουργικότητας και περιέργειας, αναγνωρίζει το αίσθημα της φιλίας και της προσωπικής ελευθερίας και αναπτύσσει πολύ γρήγορα την αγάπη για τις τέχνες, όπως αυτή της μουσικής και της γλυπτικής.

Περνώντας ταχέως τις δεκαετίες και φτάνοντας στο 2020, βλέπουμε αμυδρές εξελίξεις στην τεχνολογία της ταινίας, όπως για παράδειγμα τα ιπτάμενα αυτοκίνητα και τις αναβαθμίσεις των ρομπότ, μία εκ των οποίων είναι και η προσθήκη εκφράσεων στις επικαλυπτικές μάσκες τους. Συνεχίζοντας στο 2032 και αργότερα στο 2048, πέρα από την εξέλιξη του πρωταγωνιστή μας ως άτομο, η ταινία δεν έχει να μας δώσει κάποια περαιτέρω τεχνολογική διαφοροποίηση πέραν μίας γραφίδας-tablet. Ταυτόχρονα, σταθερά παραμένουν και τα κατά τ΄άλλα ραγδαίως εξελισσόμενα στοιχεία του πολιτισμού μας, όπως για παράδειγμα τα ρούχα, οι διακοσμήσεις των σπιτιών και των κτηρίων, ακόμα και οι εξοπλισμοί τους. Η πρώτη φορά που βλέπουμε στην ταινία αρκετές αλλαγές στα παραπάνω, είναι κατά τα έτη 2067 με 2068, όταν ο Andrew ταξιδεύει τον κόσμο και, ακολουθώντας τον, βλέπουμε τις πινακίδες των μαγαζιών ως ολογράμματα, τις σιδηροδρομικές γραμμές να έχουν εκσυγχρονιστεί με τις ράγες τους να βρίσκονται αρκετά μέτρα πάνω από το έδαφος και την αρχιτεκτονική των νοσοκομείων να θυμίζει μοντέρνους σχεδιασμούς, χωρίς φυσικά να μπορούμε να αναφέρουμε την οποιαδήποτε ακρότητα για τους μοντερνισμούς αυτούς. Για άλλη μία φορά, οι ρομποτικές εξελίξεις στην ταινία είναι πολλές παραπάνω και εμφανώς πιο σημαντικές. Την συγκεκριμένη χρονική στιγμή στην ταινία μαθαίνουμε, πως ένας επιστήμονας καταφέρνει να ενσωματώσει στα ρομπότ δέρμα παρόμοιο με αυτό των ανθρώπων, ενώ λίγα χρόνια αργότερα ο πρωταγωνιστής μας, παρέα με τον ίδιο αυτόν επιστήμονα, βρίσκει τον τρόπο για την αντικατάσταση των ρομποτικών οργάνων με όργανα, που φέρουν αρκετές ομοιότητες με αυτά των ανθρώπων. Συνεχίζουν με την ενσωμάτωση νευρικού και αναπαραγωγικού συστήματος στα ρομπότ και φτάνουν μέχρι και την δυνατότητα μεταμοσχεύσεως των τεχνητών αυτών οργάνων σε ανθρώπους. Ως αντίθεση σε όλα αυτά έρχεται η χρήση βινυλίων, τα απαράλλαχτα ρούχα και γενικώς κάθε στοιχείο της κοινωνίας του 1999, όπου δεν παρατηρούμε καμία αλλαγή και καμία εξέλιξη. Προς το τέλος της ταινίας, κατά τα έτη 2120 έως και 2140, γίνεται στην ταινία μία αναφορά στο προϊόν DNA elixir, του οποίου λειτουργία είναι η μακροζωία και η νεαν��κή εμφάνιση. Η ταινία κλείνει με τον Andrew να γίνεται εξ’ ολοκλήρου άνθρωπος και να γερνάει κανονικά μέχρι το 2205, όπου και πεθαίνει, δείχνοντάς μας ταυτόχρονα πως οι τεχνολογικές εξελίξεις έχουν φτάσει μέχρι τις βιντεοκλήσεις μέσω ολογραμμάτων.

Είναι ξεκάθαρο καθ’ όλη τη διάρκεια της ταινίας πως κύριος στόχος της δεν ήταν οι τεχνολογικές, και άλλες, εξελίξεις της κοινωνίας μας, αφού βλέπουμε να χρησιμοποιεί τις ήδη υπάρχουσες τεχνολογίες, ή να βασίζει τις μελλοντικές εξελίξεις σε τότε υπάρχουσες θεωρίες για το πώς θα ήταν η κοινωνία μας στα επόμενα χρόνια. Η βασική ιδέα της ταινίας είναι τα ρομπότ, τα οποία μπορούν να επικοινωνήσουν σαν κανονικοί άνθρωποι και υπακούουν εντολές. Αυτή η ιδέα δεν είναι καινούρια, καθώς οι ρίζες της ξεκινούν ήδη από την αρχαία Ελλάδα. Η μυθολογία λέει, πως ο θεός Ήφαιστος είχε φτιάξει ένα ρομπότ από μπρούτζο, τον Τάλο, για να προστατεύει την Ευρώπη από εισβολείς στην Κρήτη. Στη νεότερη ιστορία, το πρώτο ρομπότ που κατασκευάστηκε ποτέ, το οποίο υπάκουγε σε εντολές, ήταν το 1939 από το Westinghouse Electric Corporation. Αυτό το ρομπότ μπορούσε να υπακούσει σε έναν αριθμό εντολών, να περπατήσει, ακόμα και να μιλήσει, χωρίς βέβαια να έχει συνείδηση του τι λέει και χωρίς να έχει κάποια ιδιαίτερη ευκινησία.

Η ιδέα του ρομπότ, που μπορεί να συνεννοηθεί κανονικά και αυτόματα με τους ανθρώπους και που μπορεί να έχει συναισθήματα, ήταν πάντα στο μυαλό των ανθρώπων. Δυστυχώς, αυτό είναι πολύ πιο δύσκολο να επιτευχθεί, απ’ όσο φαίνεται. Τα συναισθήματα είναι οι ιδιωματισμοί στις εκφράσεις του σώματος και του προσώπου και στην αλλαγή της φωνής. Όπως, για παράδειγμα, το χαμόγελο και το συνοφρύωμα, ή η αλλαγή της φωνής αναλόγως το άτομο, στο οποίο μιλάς, και ο τρόπος, με τον οποίο μιλάς. Πράγματι, στη σημερινή εποχή έχουν γίνει διάφορες δοκιμές και έχουν δημιουργηθεί ρομπότ, που είναι προγραμματισμένα να εκφράζουν αυτά τα συναισθήματα. Ένα παράδειγμα είναι η “Kismet”, ένα ρομπότ που κατασκευάστηκε από την Cynthia Breazeal, το οποίο εκφράζει λύπη, χαρά και άγχος, με αποτέλεσμα να κάνει τους ανθρώπους να την αντιμετωπίζουν ως ένα νοήμον όν.

Το να έχει, ωστόσο, ένα ρομπότ συναισθήματα και νοημοσύνη σημαίνει, πως θα μπορεί να πάρει αποφάσεις σε αμφιλεγόμενες καταστάσεις. Εάν, για παράδειγμα, ένα αμάξι με τέτοιου είδους νοημοσύνη βρεθεί σε μία κατάσταση, όπου θα πρέπει να πατήσει είτε μία γιαγιά, είτε ένα μικρό παιδάκι, πως θα πάρει μία απόφαση; Εν τέλει, η τεχνολογία των ρομπότ δεν έχει προχωρήσει τόσο, ώστε να λέμε, ότι τα ρομπότ μπορούν πραγματικά να έχουν τέτοια χαρακτηριστικά. Παρ’ όλες τις υπάρχουσες ελπίδες, ένα τέτοιο σενάριο φαντάζει ουτοπικό.

Αναφορικά με τα τεχνητά ανθρώπινα όργανα, τα οποία βλέπουμε αρκετά στην ταινία, οι δημιουργοί τα ήθελαν να χρησιμοποιούνται ως μοσχεύματα σε ανθρώπους, πράμα που θα ήταν μία τεράστια επανάσταση στον ιατρικό κλάδο σε ολόκληρο τον κόσμο. Στην πραγματικότητα, φαίνεται να έχουν εμπνευστεί από πετυχημένα πειράματα με βιονικές καρδιές, που χτυπούν με τη βοήθεια μαγνητών και μεταφέρουν αίμα, όπως επίσης και από πειράματα κατασκευής νευρικού συστήματος, το οποίο μεταφέρει πληροφορίες μέσω ηλεκτρισμού. Παρόλα αυτά, το να μπορέσουν τέτοια μηχανήματα να μπούνε σε έναν ανθρώπινο οργανισμό και να λειτουργήσουν χωρίς κανένα πρόβλημα, είναι ένα δυσκολότερο ζήτημα απ’ ότι θέλουμε να πιστεύουμε.

Γενικά η ταινία, και όσο περνούν τα χρόνια, φαίνεται πως προσπαθεί λίγο να προσαρμόσει την τεχνολογία της εποχής. Βλέπουμε τάμπλετ-γραφίδες, βλέπουμε μοντερνοποιημένους χώρους σε μέρη όπως τα νοσοκομεία και τα δικαστήρια και, επιπλέον, βλέπουμε και ιπτάμενα αυτοκίνητα. Τα τάμπλετ, η αλήθεια είναι, πως υπήρχαν σαν ιδέα, καθώς τα βλέπουμε σε παλαιότερες ταινίες όπως «Η Οδύσσεια του Διαστήματος». Επίσης, κάποια από τα πρώτα πραγματικά τάμπλετ με γραφίδες που υπήρχαν, ήταν το “Samsung Pen Master Tablet”, της Samsung, το 1992 και το “Newton 20UI”, της Apple, το 1993. Όσον αφορά τους μοντέρνους χώρους, η ταινία δεν απέχει πολύ από την πραγματικότητα. Πόρτες που ανοίγουν με αισθητήρα, περισσότερα LED φώτα και πιο μοντέρνα κρεβάτια ή καθίσματα. Τα ιπτάμενα αυτοκίνητα δεν μπορούμε να γνωρίζουμε, αν πραγματικά θα υπάρξουν μέχρι το 2058, όπου τα βλέπουμε για πρώτη φορά στην ταινία, αλλά γνωρίζουμε πως είναι μία δύσκολη υπόθεση, καθώς προκαλεί σύγχυση η ιδέα της αλλαγής των νόμων και τα περισσότερα μέτρα ασφαλείας, που μπορεί να χρειαστούν. Παρόλα αυτά, τα υπόλοιπα στοιχεία της ταινία, όπως τα σπίτια, οι διακοσμήσεις και οι πολυκατοικίες-ουρανοξύστες, πλησιάζουν αρκετά τη σύγχρονη εποχή.

Βιβλιογραφία:

Columbus, C. (1999). Bicentennial Man [DVD]. United States; Chris Columbus, Wolfgang Petersen, Gail Katz, Laurence Mark, Neal Miller, Mark Roadcliff and Michael Barnathan. MAYOR, A. (2018). GODS AND ROBOTS. PRINCETON University PRES.

Elektro. Web.archive.org. (2004). Retrieved 16 June 2020, from https://web.archive.org/web/20050212022312/http:/davidszondy.com/future/robot/elektro1.htm. 1939 ELEKTRO the Smoking Robot!!! New York World's Fair. (2007). [Video]. Retrieved 16 June 2020, from https://www.youtube.com/watch?v=T35A3g_GvSg. Evans, D. (2001). Can robots have emotions? [Ebook]. Oxford University Press. Retrieved 16 June 2020, from https://www.inf.ed.ac.uk/events/hotseat/dylan_position.pdf.

Poole, L. (1996). Newton 2.0 User Interface Guidelines [Ebook]. Addison-Wesley Publishing Company. Retrieved 16 June 2020, from https://www.newted.org/download/manuals/Newton20UIGuide.pdf.

Samsung Pen Master Tablet - Computer - Computing History. Computinghistory.org.uk. (1992). Retrieved 16 June 2020, from http://www.computinghistory.org.uk/det/18733/Samsung-Pen-Master-Tablet.

Eker, U., Ahmed, S., Fountas, G., & Anastasopoulos, P. (2019). An exploratory investigation of public perceptions towards safety and security from the future use of flying cars in the United States. Analytic Methods In Accident Research, 23, 100103. https://doi.org/10.1016/j.amar.2019.100103

Xia, D. (2012). A Bionic Artificial Heart Blood Pump Driven by Permanent Magnet Located Outside Human Body. IEEE Transactions On Applied Superconductivity, 22(3), 4401304-4401304. https://doi.org/10.1109/tasc.2011.2174582

Denison, T., Morris, M., & Sun, F. (2015). Building a bionic nervous system. IEEE Spectrum, 52(2), 32-39. https://doi.org/10.1109/mspec.2015.7024509

1 note · View note

blogruthp-blog · 6 years ago

Text

The Rape of Robots

When a robot tells you he loves you, should you believe it? In recent years, technology has made great progress. Some scientists claim that there is nothing about human love and sex that could not be engineered in the relatively near future. Some go even further and argue that the bots would not only be psychologically pleasing, but that humans would prefer them to human relationships.

Nowadays we’re able to build the kind of machine that is extremely similar to a human-being, so it’s rather difficult to tell them apart. Nevertheless, it’s not a big deal to create a bot that engages the user in an emotional and irresistible way. The famous Tamagotchi, a virtual pet in a mini portable Gameboy, is a good illustration. Although Tamagotchi and a sexbot have little in common, it shows that people can get emotionally affected to an unhuman object. Lots of people have spent many hours on feeding and taking care of the artificial pet.

Latex “Sex Dolls” have existed for many years. Recent advances can design a humanoid robot with behavioral responses and fulfill sexual fantasies. With this progression of robots, publications about ethical and physical issues increase. For example, should sexbots be equipped with a behavioral repertoire, can they refuse sex as a result of an explicitly programmed script containing a series of stimuli and should it be possible for sexbots to refuse sex when sexual actions proceed beyond a certain point? Are we talking here about rape? Sexual acts without mutual consent are defined as rape. That may also include sexual actions with robots in which the bot fails to refuse. But where is the limit of a robot? It brings up some ethical questions about human interaction and a virtual world.

“Is it wrong to rape a robot?”, is an ethical question that arises when we talk about sexbots. On the one hand, when a robot explicitly refuses sex, it would be unethical because it is a simulation of having sex with a real woman or man who refuses intercourse and it would facilitate rape fantasy. As a result, it could increase real rape. On the other hand, bots that lack the capacity of refusing can give an unrealistic representation of sexual activity. Both situations cause discussions and create divisions in the ethical debate about having sex with robots.

References

Sparrow, Robert. “Robots, Rape, and Representation”. International Journal of Social Robotics 9, nr. 4 (1 september 2017): 465–77. https://doi.org/10.1007/s12369-017-0413-z.

Sullins, John P. “Robots, Love, and Sex: The Ethics of Building a Love Machine”. IEEE Transactions on Affective Computing 3, nr. 4 (Fourth 2012): 398–409. https://doi.org/10.1109/T-AFFC.2012.31.

4 notes · View notes

drmikewatts · 12 days ago

Text

IEEE Transactions on Artificial Intelligence, Volume 6, Issue 6, June 2025

1) GLAC-GCN: Global and Local Topology-Aware Contrastive Graph Clustering Network

Author(s): Yuan-Kun Xu, Dong Huang, Chang-Dong Wang, Jian-Huang Lai

Pages: 1448 - 1459

2) Unsupervised Action Recognition Using Spatiotemporal, Adaptive, and Attention-Guided Refining-Network

Author(s): Xinpeng Yin, Cheng Zhang, ZiXu Huang, Zhihai He, Wenming Cao

Pages: 1460 - 1471

3) MRI Joint Superresolution and Denoising Based on Conditional Stochastic Normalizing Flow

Author(s): Zhenhong Liu, Xingce Wang, Zhongke Wu, Xiaodong Ju, YiCheng Zhu, Alejandro F. Frangi

Pages: 1472 - 1487

4) Federated Multiarmed Bandits Under Byzantine Attacks

Author(s): Artun Saday, İlker Demirel, Yiğit Yıldırım, Cem Tekin

Pages: 1488 - 1501

5) Dynamically Scaled Temperature in Self-Supervised Contrastive Learning

Author(s): Siladittya Manna, Soumitri Chattopadhyay, Rakesh Dey, Umapada Pal, Saumik Bhattacharya

Pages: 1502 - 1512

6) Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs

Author(s): Tiehua Zhang, Yuze Liu, Zhishu Shen, Xingjun Ma, Peng Qi, Zhijun Ding, Jiong Jin

Pages: 1513 - 1528

7) A Spatial-Transformation-Based Causality-Enhanced Model for Glioblastoma Progression Diagnosis

Author(s): Qiang Li, Xinyue Li, Hong Jiang, Xiaohua Qian

Pages: 1529 - 1539

8) From Global to Hybrid: A Review of Supervised Deep Learning for 2-D Image Feature Representation

Author(s): Xinyu Dong, Qi Wang, Hongyu Deng, Zhenguo Yang, Weijian Ruan, Wu Liu, Liang Lei, Xue Wu, Youliang Tian

Pages: 1540 - 1560

9) Leveraging AI to Compromise IoT Device Privacy by Exploiting Hardware Imperfections

Author(s): Mirza Athar Baig, Asif Iqbal, Muhammad Naveed Aman, Biplab Sikdar

Pages: 1561 - 1574

10) CVDLLM: Automated Cardiovascular Disease Diagnosis With Large-Language-Model-Assisted Graph Attentive Feature Interaction

Author(s): Xihe Qiu, Haoyu Wang, Xiaoyu Tan, Yaochu Jin

Pages: 1575 - 1590

11) Neural Network Output-Feedback Distributed Formation Control for NMASs Under Communication Delays and Switching Network

Author(s): Haodong Zhou, Shaocheng Tong

Pages: 1591 - 1602

12) t-SNVAE: Deep Probabilistic Learning With Local and Global Structures for Industrial Process Monitoring

Author(s): Jian Huang, Zizhuo Liu, Xu Yang, Yupeng Liu, Zhaomin Lv, Kaixiang Peng, Okan K. Ersoy

Pages: 1603 - 1613

13) SpikeNAS-Bench: Benchmarking NAS Algorithms for Spiking Neural Network Architecture

Author(s): Gengchen Sun, Zhengkun Liu, Lin Gan, Hang Su, Ting Li, Wenfeng Zhao, Biao Sun

Pages: 1614 - 1625

14) AttDCT: Attention-Based Deep Learning Approach for Time Series Classification in the DCT Domain

Author(s): Amine Haboub, Hamza Baali, Abdesselam Bouzerdoum

Pages: 1626 - 1638

15) Behavioral Decision-Making of Mobile Robots Simulating the Functions of Cerebellum, Basal Ganglia, and Hippocampus

Author(s): Dongshu Wang, Qi Liu, Yihai Duan

Pages: 1639 - 1650

16) Learning From Mistakes: A Multilevel Optimization Framework

Author(s): Li Zhang, Bhanu Garg, Pradyumna Sridhara, Ramtin Hosseini, Pengtao Xie

Pages: 1651 - 1663

17) COLT: Cyclic Overlapping Lottery Tickets for Faster Pruning of Convolutional Neural Networks

Author(s): Md. Ismail Hossain, Mohammed Rakib, M. M. Lutfe Elahi, Nabeel Mohammed, Shafin Rahman

Pages: 1664 - 1678

18) HWEFIS: A Hybrid Weighted Evolving Fuzzy Inference System for Nonstationary Data Streams

Author(s): Tao Zhao, Haoli Li

Pages: 1679 - 1694

#ai #artificial intelligence

0 notes

roboticsappreciationsociety · 6 years ago

Link

A movie montage for modern artificial intelligence might show a computer playing millions of games of chess or Go against itself to learn how to win. Now, researchers are exploring how the reinforcement learning technique that helped DeepMind’s AlphaZero conquer chess and Go could tackle an even more complex task—training a robotic knee to help amputees walk smoothly.

This new application of AI, which is based on reinforcement learning—an automated version of classic trial-and-error—has shown promise in small clinical experiments involving one able-bodied person and one amputee whose leg was cut off above the knee. Normally, human technicians spend hours working with amputees to manually adjust robotic limbs to work well with each person’s style of walking. By comparison, the reinforcement-learning technique automatically tuned a robotic knee, enabling the prosthetic wearers to walk smoothly on level ground within 10 minutes.

“If you wanted to make this clinically relevant, there are many, many steps that we have to go through before this can happen,” says Helen Huang, a professor in biomedical engineering at both North Carolina State University and the University of North Carolina. “So far it’s really just to show it’s possible. By itself that’s very, very exciting.”

Huang and her colleagues published their findings on 16 January 2019 in IEEE Transactions on Cybernetics. Their study marks a possible first step toward automating the typical manual tuning process that requires costly and time-consuming clinic visits whenever robotic limbs need adjusting—something that could also eventually allow prosthetic users to tune their robotic limbs at home or on the go.

The tuning process focuses on specific parameters that define the relationship between force and motion in using a robotic limb. For example, some parameters may define the stiffness of the robotic knee joint or the range of motion allowed in swinging a leg back and forth. In this case, the robotic knee had a dynamic combination of 12 parameters that required trial-and-error tuning. The starting point for such parameters are usually far from perfect for freshly unboxed robotic limbs, but enough for wearers to stand up and make simple walking movements.

Training a robotic limb is a complex process of co-adaptation that requires the limb to learn how to cooperate with the human brain controlling most of the body. That process can involve much initial clumsiness: not unlike the first time people strap skis onto their feet and try to move around on a snow-packed surface.

“Our body does weird things when we have a foreign object on our body,” says Jennie Si, professor of electrical, computer, and energy engineering at Arizona State University and coauthor of the paper. “In some sense, our computer reinforcement learning algorithm learns to cooperate with the human body.”

To complicate matters further, the reinforcement-learning algorithm had to prove its worth with a fairly limited set of training data from prosthetics users. When DeepMind trained its AlphaZero computer program to master games such as chess and Go, AlphaZero had the benefit of being able to simulate millions of games during its marathon training montage. By comparison, individual human amputees cannot keep walking forever for the sake of training a reinforcement algorithm—those who visit Huang’s lab may walk just 15 or 20 minutes before taking a rest break.

The training data also faced other limitations. At the beginning of the research project, Si wondered if it was possible to allow the prosthetics users to fall down during some trial runs so that the algorithm could learn from those cases. But Huang rejected that idea for safety reasons.

Despite such challenges, initial results have proven promising. The researchers trained the reinforcement-learning algorithm to recognize certain patterns in the data collected from sensors embedded in the prosthetic knee and set some initial constraints on their algorithm to avoid more undesirable situations that could cause the wearer to fall down. Eventually, the algorithm learned to focus on certain data patterns that matched fairly stable and smooth walking patterns.

This automated approach to tuning robotic limbs is far from ready for widespread deployment. For now, the researchers plan to train the algorithm to help prosthetic users walk up and down steps. They also hope to create a wireless version of the system that could extend training sessions beyond in-person visits to the lab.

One of the biggest next steps for the research project involves somehow giving prosthetics users a way to tell the algorithm that a particular walking pattern feels better or worse. But early attempts to allow for human input via a button or other simple controls have proven somewhat clumsy in practice—perhaps in part because such input fails to capture the complex coordination of human perception and cognition in choreographing a body’s movements.

“It hasn’t really worked out well because we don’t really understand humans well,” Huang says. “I definitely see a lot of basic science that needs to be done to jump there.”

#robot #robotics #prosthetics #artificial intelligence

30 notes · View notes

neurosciencenews · 6 years ago

Photo

Reinforcement Learning Expedites 'Tuning' of Robotics Prosthetics

Researchers have developed an intelligent system for "tuning" powered prosthetic knees, allowing patients to walk comfortably with the prosthetic device in minutes, rather than the hours necessary if the device is tuned by a trained clinical practitioner.

The system is the first to rely solely on reinforcement learning to tune the robotic prosthesis.

The research is in IEEE Transactions on Cybernetics. (full access paywall)

#prosthetics #neuroprosthesis #neuroprosthetics #neurotech #neurobotics #robotic prosthetics #neuroscience #science

26 notes · View notes

compneuropapers · 6 years ago

Text

Interesting Papers for Week 19, 2019

Schema cells in the macaque hippocampus. Baraduc, P., Duhamel, J.-R., & Wirth, S. (2019). Science, 363(6427), 635–639.

Human consciousness is supported by dynamic complex patterns of brain signal coordination. Demertzi, A., Tagliazucchi, E., Dehaene, S., Deco, G., Barttfeld, P., Raimondo, F., … Sitt, J. D. (2019). Science Advances, 5(2), eaat7603.

Large and fast human pyramidal neurons associate with intelligence. Goriounova, N. A., Heyer, D. B., Wilbers, R., Verhoog, M. B., Giugliano, M., Verbist, C., … Mansvelder, H. D. (2018). eLife, 7, e41714.

Topological Control of Synchronization Patterns: Trading Symmetry for Stability. Hart, J. D., Zhang, Y., Roy, R., & Motter, A. E. (2019). Physical Review Letters, 122(5), 058301.

Attention Enhances the Efficacy of Communication in V1 Local Circuits. Hembrook-Short, J. R., Mock, V. L., Usrey, W. M., & Briggs, F. (2019). Journal of Neuroscience, 39(6), 1066–1076.

Rocking Promotes Sleep in Mice through Rhythmic Stimulation of the Vestibular System. Kompotis, K., Hubbard, J., Emmenegger, Y., Perrault, A., Mühlethaler, M., Schwartz, S., … Franken, P. (2019). Current Biology, 29(3), 392-401.e4.

Robot–Robot Gesturing for Anchoring Representations. Kondaxakis, P., Gulzar, K., Kinauer, S., Kokkinos, I., & Kyrki, V. (2019). IEEE Transactions on Robotics, 35(1), 216–230.

Agent-based representations of objects and actions in the monkey pre-supplementary motor area. Livi, A., Lanzilotto, M., Maranesi, M., Fogassi, L., Rizzolatti, G., & Bonini, L. (2019). Proceedings of the National Academy of Sciences of the United States of America, 116(7), 2691–2700.

Inhibition of Nigrostriatal Dopamine Release by Striatal GABAA and GABAB Receptors. Lopes, E. F., Roberts, B. M., Siddorn, R. E., Clements, M. A., & Cragg, S. J. (2019). Journal of Neuroscience, 39(6), 1058–1065.

Getting closer to the goal by being less capable. Manrique, P. D., Klein, M., Li, Y. S., Xu, C., Hui, P. M., & Johnson, N. F. (2019). Science Advances, 5(2), eaau5902.

Information seeking mechanism of neural populations in the lateral prefrontal cortex. Nakamura, K., & Komatsu, M. (2019). Brain Research, 1707, 79–89.

Mechanisms of Spatiotemporal Selectivity in Cortical Area MT. Pawar, A. S., Gepshtein, S., Savel’ev, S., & Albright, T. D. (2019). Neuron, 101(3), 514-527.e2.

Whole-Night Continuous Rocking Entrains Spontaneous Neural Oscillations with Benefits for Sleep and Memory. Perrault, A. A., Khani, A., Quairiaux, C., Kompotis, K., Franken, P., Muhlethaler, M., … Bayer, L. (2019). Current Biology, 29(3), 402-411.e3.

Saccadic eye movements smear spatial working memory. Peterson, M. S., Kelly, S. P., & Blumberg, E. J. (2019). Journal of Experimental Psychology: Human Perception and Performance, 45(2), 255–263.

Deconstructing Theory-of-Mind Impairment in High-Functioning Adults with Autism. Rosenthal, I. A., Hutcherson, C. A., Adolphs, R., & Stanley, D. A. (2019). Current Biology, 29(3), 513-519.e6.

Layer-Specific Physiological Features and Interlaminar Interactions in the Primary Visual Cortex of the Mouse. Senzai, Y., Fernandez-Ruiz, A., & Buzsáki, G. (2019). Neuron, 101(3), 500-513.e5.

Postretrieval Relearning Strengthens Hippocampal Memories via Destabilization and Reconsolidation. Tay, K. R., Flavell, C. R., Cassini, L., Wimber, M., & Lee, J. L. C. (2019). Journal of Neuroscience, 39(6), 1109–1118.

Stimulus Context and Reward Contingency Induce Behavioral Adaptation in a Rodent Tactile Detection Task. Waiblinger, C., Wu, C. M., Bolus, M. F., Borden, P. Y., & Stanley, G. B. (2019). Journal of Neuroscience, 39(6), 1088–1099.

A Dendritic Substrate for the Cholinergic Control of Neocortical Output Neurons. Williams, S. R., & Fletcher, L. N. (2019). Neuron, 101(3), 486-499.e4.

Information-Theoretic Intrinsic Plasticity for Online Unsupervised Learning in Spiking Neural Networks. Zhang, W., & Li, P. (2019). Frontiers in Neuroscience, 13, 31.

#science #Neuroscience #computational neuroscience #Brain science #research #neurobiology #psychophysics #machine learning #cognition #cognitive science #scientific publications

3 notes · View notes