Learning Sequence Attractors in Recurrent Networks with Hidden Neurons

Yao Lu, Si Wu

Primary Area: applications to neuroscience & cognitive science

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: neural networks, attractor networks, threshold networks, sequence attractors, sequence memory, episodic memory

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: The brain is targeted for processing temporal sequence information. It remains largely unclear how the brain learns to store and retrieve sequence memories. Here, we study how recurrent networks of binary neurons learn sequence attractors to store predefined pattern sequences and retrieve them robustly. We show that to store arbitrary pattern sequences, it is necessary for a recurrent network to include hidden neurons even though their role in displaying sequence memories is indirect. We develop a local learning algorithm to learn sequence attractors in recurrent networks with hidden neurons. The algorithm is proved to converge and produce sequence attractors. We demonstrate our model can learn and retrieve sequences robustly on synthetic and real-world datasets. We hope that this study provides new insights in understanding temporal information processing in the brain.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3994