Code-specific learning rules improve action selection by populations of spiking neurons

Friedrich, Johannes; Urbanczik, Robert; Senn, Walter (2014). Code-specific learning rules improve action selection by populations of spiking neurons. International Journal of Neural Systems, 24(5), p. 1450002. World Scientific Publishing 10.1142/S0129065714500026

[img] Text
IJNSpreprint.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (848kB)

Population coding is widely regarded as a key mechanism for achieving reliable behavioral decisions. We previously introduced reinforcement learning for population-based decision making by spiking neurons. Here we generalize population reinforcement learning to spike-based plasticity rules that take account of the postsynaptic neural code. We consider spike/no-spike, spike count and spike latency codes. The multi-valued and continuous-valued features in the postsynaptic code allow for a generalization of binary
decision making to multi-valued decision making and continuous-valued action selection. We show that code-specific learning rules speed up learning both for the discrete classification and the continuous regression tasks. The suggested learning rules also speed up with increasing population size as opposed to standard reinforcement learning rules. Continuous action selection is further shown to explain realistic learning speeds in the Morris water maze. Finally, we introduce the concept of action perturbation as
opposed to the classical weight- or node-perturbation as an exploration mechanism underlying reinforcement learning. Exploration in the action space greatly increases the speed of learning as compared to exploration in the neuron or weight space.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Pre-clinic Human Medicine > Institute of Physiology
10 Strategic Research Centers > Center for Cognition, Learning and Memory (CCLM)

UniBE Contributor:

Friedrich, Johannes, Urbanczik, Robert, Senn, Walter

Subjects:

600 Technology > 610 Medicine & health

ISSN:

0129-0657

Publisher:

World Scientific Publishing

Language:

English

Submitter:

Stefan von Känel-Zimmermann

Date Deposited:

13 Jun 2014 13:48

Last Modified:

05 Dec 2022 14:29

Publisher DOI:

10.1142/S0129065714500026

PubMed ID:

24875790

BORIS DOI:

10.7892/boris.42827

URI:

https://boris.unibe.ch/id/eprint/42827

Actions (login required)

Edit item Edit item
Provide Feedback