Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The code and the parameter values are available at https://github.com/esinyavuz/Input-Modulation-Learning.
References
Cassenaer, S., Laurent, G.: Hebbian STDP in mushroom bodies facilitates the synchronous flow of olfactory information in locusts. Nature 448(7154), 709–713 (2007)
Denker, M., Finke, R., Schaupp, F., Grün, S., Menzel, R.: Neural correlates of odor learning in the honeybee antennal lobe. Eur. J. Neurosci. 31(1), 119–133 (2010)
Devaud, J.M., Blunk, A., Podufall, J., Giurfa, M., Grünewald, B.: Using local anaesthetics to block neuronal activity and map specific learning tasks to the mushroom bodies of an insect brain. Eur. J. Neurosci. 26(11), 3193–3206 (2007)
Ditzen, M.: Odor concentration and identity coding in the antennal lobe of the honeybee Apis Mellifera. Ph.D. thesis, Freie Universität Berlin (2005)
Faber, T., Joerges, J., Menzel, R.: Associative learning modifies neural representations of odors in the insect brain. Nat. Neurosci. 2(1), 74–78 (1999)
Guerrieri, F., Schubert, M., Sandoz, J.C., Giurfa, M.: Perceptual and neural olfactory similarity in honeybees. PLoS Biol. 3(4), e60 (2005)
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)
Huerta, R., Nowotny, T., Garcia-Sanchez, M., Abarbanel, H.D.I., Rabinovich, M.I.: Learning classification in the olfactory system of insects. Neural Comput. 16, 1601–1640 (2004)
Kemenes, I., Straub, V.A., Nikitin, E.S., Staras, K., O’Shea, M., Kemenes, G., Benjamin, P.R.: Role of delayed nonsynaptic neuronal plasticity in long-term associative memory. Curr. Biol. 16(13), 1269–1279 (2006)
Krofczik, S., Menzel, R., Nawrot, M.P.: Rapid odor processing in the honeybee antennal lobe network. Front Comput. Neurosci. 2, 1–13 (2008)
Malun, D., Giurfa, M., Galizia, C.G., Plath, N., Brandt, R., Gerber, B., Eisermann, B.: Hydroxyurea-induced partial mushroom body ablation does not affect acquisition and retention of olfactory differential conditioning in honeybees. J. Neurobiol. 53(3), 343–360 (2002)
Menzel, R.: The honeybee as a model for understanding the basis of cognition. Nat. Rev. Neurosci. 13(11), 758–768 (2012)
Münch, D., Schmeichel, B., Silbering, A.F., Galizia, C.G.: Weaker ligands can dominate an odor blend due to syntopic interactions. Chem. Sens. 38, 293–304 (2013). bjs138
Nowotny, T., Stierle, J.S., Galizia, C.G., Szyszka, P.: Data-driven honeybee antennal lobe model suggests how stimulus-onset asynchrony can aid odour segregation. Brain Res. 1536, 119–134 (2013)
Rath, L., Galizia, C.G., Szyszka, P.: Multiple memory traces after associative learning in the honey bee antennal lobe. Eur. J. Neurosci. 34(2), 352–360 (2011)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (1998)
Traub, R.D., Miles, R.: Neuronal Networks of the Hippocampus, vol. 777. Cambridge University Press, Cambridge (1991)
Yavuz, E., Turner, J., Nowotny, T.: GeNN: a code generation framework for accelerated brain simulations. Sci. Rep. 6, 18854 (2016)
Acknowledgments
This work is supported by the EPSRC (Green Brain Project, grant number EP/J019690/1) and Human Frontiers Science Program, grant number RGP0053/2015.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Yavuz, E., Nowotny, T. (2016). Input-Modulation as an Alternative to Conventional Learning Strategies. In: Villa, A., Masulli, P., Pons Rivero, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2016. ICANN 2016. Lecture Notes in Computer Science(), vol 9886. Springer, Cham. https://doi.org/10.1007/978-3-319-44778-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-44778-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44777-3
Online ISBN: 978-3-319-44778-0
eBook Packages: Computer ScienceComputer Science (R0)