2020/06/09 by Nicolas Vecoven, Damien Ernst, Guillaume Drion · 25 citations
Computer Science · Engineering · Neuroscience · #Advanced Memory and Neural Computing #Algorithm #Artificial intelligence #Artificial neural network #Biology #Bistability #Computer science #Gating #Neural Networks and Reservoir Computing #Neural dynamics and brain function #Neuromodulation #Neuron #Neuroscience #Physics #Process (computing) #Recurrent neural network #State (computer science) #cs.LG #cs.NE
paper · pdf · doi:10.1371/journal.pone.0252676
published in PLoS ONE 16(6), e0252676 (Public Library of Science)
arxiv created 2020/06/09 · openalex publication_date 2021/06/08 · arxiv updated 2021/07/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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. With this link, this work paves the way for studying more complex and biologically plausible neuromodulation schemes as gating mechanisms in RNNs.