TL;DR
This paper introduces a biologically-inspired bistable recurrent cell for RNNs, enabling long-lasting memory at the cellular level, and enhances biological plausibility by linking it with neuromodulation and standard GRU cells.
Contribution
The paper proposes a novel bistable recurrent cell inspired by biological neurons, improving long-term memory in RNNs using only cellular connections.
Findings
Significantly improves RNN performance on long-memory time-series tasks.
Demonstrates durable memory retention through cellular bistability.
Links the bistable cell to GRU via neuromodulation, enhancing biological plausibility.
Abstract
Recurrent neural networks (RNNs) provide state-of-the-art performances in a wide variety of tasks that require memory. These performances can often be achieved thanks to gated recurrent cells such as gated recurrent units (GRU) and long short-term memory (LSTM). Standard gated cells share a layer internal state to store information at the network level, and long term memory is shaped by network-wide recurrent connection weights. Biological neurons on the other hand are capable of holding information at the cellular level for an arbitrary long amount of time through a process called bistability. Through bistability, cells can stabilize to different stable states depending on their own past state and inputs, which permits the durable storing of past information in neuron state. In this work, we take inspiration from biological neuron bistability to embed RNNs with long-lasting memory at…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
A bio-inspired bistable recurrent cell allows for long-lasting memory (Paper Explained)· youtube
Taxonomy
MethodsGated Recurrent Unit
