A Brain-inspired Computational Model for Spatio-temporal Sequence Recognition
報告人簡介
弭元元，清華大學心理與認知科學系長聘副教授。畢業于北京師范大學物理學系，先后在以色列Weizmann Institute of Science和美國Columbia University做博士后。研究方向為計算神經科學。專注于采用數理建模和計算仿真的方法研究腦在網絡層面處理動態信息的一般性原理，包括工作記憶的容量與調控、時空信息的網絡編碼等；并基于此發展了類腦運動模式的快速識別算法、運動目標的預測追蹤算法等。以第一或通訊（含共同）在神經科學領域刊物Neuron, PNAS, Progress in Neurobiology等，和人工智能領域的頂級國際會議NeurIPS，Neural Networks等，發表論文20余篇。獲得國家自然科學基金委交叉學部優秀青年基金（2021年），北京市科技新星（2017年）等項目的支持。
內容簡介
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.
