Gradient Learning in Spiking Neural Networks by Dynamic Perturbation of Conductances

Journal Article · Fri Jul 28 00:00:00 EDT 2006 · Physical Review Letters

DOI:https://doi.org/10.1103/PHYSREVLETT.97.048104· OSTI ID:20860584

Fiete, Ila R ^[1]; Seung, H Sebastian ^[2]

---

1. Kavli Institute for Theoretical Physics, University of California, Santa Barbara, California 93106 (United States)
2. Howard Hughes Medical Institute and Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139 (United States)

We present a method of estimating the gradient of an objective function with respect to the synaptic weights of a spiking neural network. The method works by measuring the fluctuations in the objective function in response to dynamic perturbation of the membrane conductances of the neurons. It is compatible with recurrent networks of conductance-based model neurons with dynamic synapses. The method can be interpreted as a biologically plausible synaptic learning rule, if the dynamic perturbations are generated by a special class of 'empiric' synapses driven by random spike trains from an external source.

• OSTI ID: 20860584
• Journal Information: Physical Review Letters, Vol. 97, Issue 4; Other Information: DOI: 10.1103/PhysRevLett.97.048104; (c) 2006 The American Physical Society; Country of input: International Atomic Energy Agency (IAEA); ISSN 0031-9007
• Country of Publication: United States
• Language: English

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
FLUCTUATIONS
FUNCTIONS
LEARNING
MEMBRANES
NERVE CELLS
NEURAL NETWORKS
PERTURBATION THEORY
RANDOMNESS