Input-Modulation as an Alternative to Conventional Learning Strategies
Animals use various strategies for learning stimulus-reward associations. Computational methods that mimic animal behaviour most commonly interpret learning as a high level phenomenon, in which the pairing of stimulus and reward leads to plastic changes in the final output layers where action selection takes place. Here, we present an alternative input-modulation strategy for forming simple stimulus-response associations based on reward. Our model is motivated by experimental evidence on modulation of early brain regions by reward signalling in the honeybee. The model can successfully discriminate dissimilar odours and generalise across similar odours, like bees do. In the most simplified connectionist description, the new input-modulation learning is shown to be asymptotically equivalent to the standard perceptron.
KeywordsReinforcement learning Olfactory system Spiking neural network
This work is supported by the EPSRC (Green Brain Project, grant number EP/J019690/1) and Human Frontiers Science Program, grant number RGP0053/2015.
- 4.Ditzen, M.: Odor concentration and identity coding in the antennal lobe of the honeybee Apis Mellifera. Ph.D. thesis, Freie Universität Berlin (2005)Google Scholar
- 7.Hammer, M., Menzel, R.: Multiple sites of associative odor learning as revealed by local brain microinjections of octopamine in honeybees. Learn Mem. 5(1), 146–156 (1998)Google Scholar
- 16.Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (1998)Google Scholar