A bio-inspired bistable recurrent cell allows for long-lasting memory

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 the cellular level. This leads to the introduction of a new bistable biologically-inspired recurrent cell that is shown to strongly improves RNN performance on time-series which require very long memory, despite using only cellular connections (all recurrent connections are from neurons to themselves, i.e. a neuron state is not influenced by the state of other neurons). Furthermore, equipping this cell with recurrent neuromodulation permits to link them to standard GRU cells, taking a step towards the biological plausibility of GRU.

References in corpus (3)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• On the difficulty of training Recurrent Neural Networks
• Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets

Cited by in corpus (4)

• Multiplexing-based control of stochastic resonance
• Two-color optically-addressed spatial light modulator as generic spatio-temporal systems
• Multiplexing-based control of wavefront propagation: the interplay of inter-layer coupling, asymmetry and noise
• Spike-based computation using classical recurrent neural networks