A Brain-inspired Computational Model for Spatio-temporal Sequence Recognition
报告人简介
弭元元，清华大学心理与认知科学系长聘副教授。毕业于北京师范大学物理学系，先后在以色列Weizmann Institute of Science和美国Columbia University做博士后。研究方向为计算神经科学。专注于采用数理建模和计算仿真的方法研究脑在网络层面处理动态信息的一般性原理，包括工作记忆的容量与调控、时空信息的网络编码等；并基于此发展了类脑运动模式的快速识别算法、运动目标的预测追踪算法等。以第一或通讯（含共同）在神经科学领域刊物Neuron, PNAS, Progress in Neurobiology等，和人工智能领域的顶级国际会议NeurIPS，Neural Networks等，发表论文20余篇。获得国家自然科学基金委交叉学部优秀青年基金（2021年），北京市科技新星（2017年）等项目的支持。
内容简介
Temporal sequence processing is fundamental in brain cognitive functions. Experimental data has indicated that the representations of ordinal information and contents of temporal sequences are disentangled in the brain, but the neural mechanism underlying this disentanglement remains largely unclear. We investigate how recurrent neural circuits learn to represent the abstract order structure of temporal sequences, and how the disentangled representation of order structure facilitates the processing of temporal sequences. We show that with an appropriate training protocol, a recurrent neural circuit can learn tree-structured attractor dynamics to encode the corresponding tree-structured orders of temporal sequences. This abstract temporal order template can then be bound with different contents, allowing for flexible and robust temporal sequence processing. Using a transfer learning task, we demonstrate that the reuse of a temporal order template facilitates the acquisition of new temporal sequences, if these sequences share the same or partial ordinal structure. Using a key-word spotting task, we demonstrate that the tree-structured attractor dynamics improves the robustness of temporal sequence discrimination, if the ordinal information is the key to differentiate these sequences.
