In complex systems, we often observe complex global behavior emerge from a collection of agents interacting with each other in their environment, with each individual agent acting only on locally available information, without knowing the full picture. Such systems have inspired development of artificial intelligence algorithms in areas such as swarm optimization and cellular automata. Motivated by the emergence of collective behavior from complex cellular systems, we build systems that feed each sensory input from the environment into distinct, but identical neural networks, each with no fixed relationship with one another. We show that these sensory networks can be trained to integrate information received locally, and through communication via an attention mechanism, can collectively produce a globally coherent policy. Moreover, the system can still perform its task even if the ordering of its inputs is randomly permuted several times during an episode. These permutation invariant systems also display useful robustness and generalization properties that are broadly applicable. Interactive demo and videos of our results: https://attentionneuron.github.io/
Learn to integrate parts for whole through correlated neural variability
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University（复旦大学生脑启发智能科学技术研究院）；Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University), Ministry of Education（教育部计算神经科学与大脑启发智能重点实验室（复旦大学））；MOE Frontiers Center for Brain Science, Fudan University（复旦大学教育部前沿脑科学中心）；Zhangjiang Fudan International Innovation Center（张江复旦国际创新中心）；School of Mathematical Sciences, Fudan University（复旦大学数学科学学院）；Shanghai Center for Mathematical Sciences（上海数学中心）；Shanghai Key Laboratory for Contemporary Applied Mathematics（上海当代应用数学重点实验室）；Key Laboratory of Mathematics for Nonlinear Science（非线性科学数学重点实验室）
Motif-topology and Reward-learning improved Spiking Neural Network for Efficient Multi-sensory Integration
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）；School of Information and Electronics, Beijing Institute of Technology（北京理工大学信息与电子学院）
Functional neural network for decision processing, a racing network of programmable neurons with fuzzy logic where the target operating model relies on the network itself
The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns
Zurich University of Applied Sciences（苏黎世应用科学大学）；University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Frankfurt Institute for Advanced Studies（法兰克福高级研究 institute）
Soft Matching Distance: A metric on neural representations that captures single-neuron tuning
McGovern Institute for Brain Research（麦戈文脑研究所）；Massachusetts Institute for Technology（麻省理工学院）；Center for Neural Science, New York University（纽约大学神经科学中心）；Center for Computational Neuroscience（计算神经科学中心）；Flatiron Institute（熨斗研究所）
