Cortical microcircuits as gated-recurrent neural networks
This work provides a step towards unifying machine learning recurrent networks with biological cortical circuits, though it is incremental in nature.
The authors tackled the problem of identifying common computational principles in stereotyped cortical microcircuits by proposing a gated-recurrent neural network (subLSTM) mapped onto excitatory-inhibitory circuits. They found that subLSTM units achieve similar performance to LSTM units in sequential image classification and language modeling tasks.
Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas. Such stereotyped structure suggests the existence of common computational principles. However, such principles have remained largely elusive. Inspired by gated-memory networks, namely long short-term memory networks (LSTMs), we introduce a recurrent neural network in which information is gated through inhibitory cells that are subtractive (subLSTM). We propose a natural mapping of subLSTMs onto known canonical excitatory-inhibitory cortical microcircuits. Our empirical evaluation across sequential image classification and language modelling tasks shows that subLSTM units can achieve similar performance to LSTM units. These results suggest that cortical circuits can be optimised to solve complex contextual problems and proposes a novel view on their computational function. Overall our work provides a step towards unifying recurrent networks as used in machine learning with their biological counterparts.