PT  - JOURNAL ARTICLE
AU  - Jonathan Cornford
AU  - Damjan Kalajdzievski
AU  - Marco Leite
AU  - Amélie Lamarquette
AU  - Dimitri M. Kullmann
AU  - Blake Richards
TI  - Learning to live with Dale’s principle: ANNs with separate excitatory and inhibitory units
AID  - 10.1101/2020.11.02.364968
DP  - 2020 Jan 01
TA  - bioRxiv
PG  - 2020.11.02.364968
4099  - http://biorxiv.org/content/early/2020/11/03/2020.11.02.364968.short
4100  - http://biorxiv.org/content/early/2020/11/03/2020.11.02.364968.full
AB  - The units in artificial neural networks (ANNs) can be thought of as abstractions of biological neurons, and ANNs are increasingly used in neuroscience research. However, there are many important differences between ANN units and real neurons. One of the most notable is the absence of Dale’s principle, which ensures that biological neurons are either exclusively excitatory or inhibitory. Dale’s principle is typically left out of ANNs because its inclusion impairs learning. This is problematic, because one of the great advantages of ANNs for neuroscience research is their ability to learn complicated, realistic tasks. Here, by taking inspiration from feedforward inhibitory interneurons in the brain we show that we can develop ANNs with separate populations of excitatory and inhibitory units that learn just as well as standard ANNs. We call these networks Dale’s ANNs (DANNs). We present two insights that enable DANNs to learn well: (1) DANNs are related to normalization schemes, and can be initialized such that the inhibition centres and standardizes the excitatory activity, (2) updates to inhibitory neuron parameters should be scaled using corrections based on the Fisher Information matrix. These results demonstrate how ANNs that respect Dale’s principle can be built without sacrificing learning performance, which is important for future work using ANNs as models of the brain. The results also may have interesting implications for how inhibitory plasticity in the real brain operates.Competing Interest StatementThe authors have declared no competing interest.