On efficient sparse spike coding schemes for learning natural scenes in the primary visual cortex
This work seeks how to :
- derive an algorithm of blind source separation of low complexity on neuronal hardware,
- study the corresponding neuronal learning algorithm as implementing ICA,
compare it with the existing SparseNet solution from Bruno Olshausen,
It should be red along with
Publications/Perrinet04tauc which proposes a link with Bayesian analysis
Publications/Perrinet05icann which proposes a simple implementation with Integrate-and-Fire neurons
Publications/Perrinet06cns which exposed first results on efficiency
- Laurent Perrinet. On efficient sparse spike coding schemes for learning natural scenes in the primary visual cortex, URL . In Sixteenth Annual Computational Neuroscience Meeting: CNS*2007, Toronto, Canada. 7--12 July 2007, 2007 abstractWe describe the theoretical formulation of a learning algorithm in a model of the primary visual cortex (V1) and present results of the efficiency of this algorithm by comparing it to the SparseNet algorithm . As the SparseNet algorithm, it is based on a model of signal synthesis as a Linear Generative Model but differs in the efficiency criteria for the representation. This learning algorithm is in fact based on an efficiency criteria based on the Occam razor: for a similar quality, the shortest representation should be privileged. This inverse problem is NP-complete and we propose here a greedy solution which is based on the architecture and nature of neural computations ). It proposes that the supra-threshold neural activity progressively removes redundancies in the representation based on a correlation-based inhibition and provides a dynamical implementation close to the concept of neural assemblies from Hebb ). We present here results of simulation of this network with small natural images (available at http://invibe.net/LaurentPerrinet/SparseHebbianLearning) and compare it to the Sparsenet solution. Extending it to realistic images and to the NEST simulator http://www.nest-initiative.org/, we show that this learning algorithm based on the properties of neural computations produces adaptive and efficient representations in V1. 1. Olshausen B, Field DJ: Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Res 1997, 37:3311-3325.2. Perrinet L: Feature detection using spikes: the greedy approach. J Physiol Paris 2004, 98(4–6):530-539.3. Hebb DO: The organization of behavior. Wiley, New York; 1949..
All material (c) L. Perrinet. Please check the copyright notice.