Neuromorphic Adaptable Ocular Dominance Maps
Time staggered winner-take-all (ts-WTA) is a novel analog CMOS neuron cell , that computes ‘sum of weighted inputs” implemented as floating gate pFET ‘synapses’. The cell behavior exhibits competitive learning (WTA) so as to refine its weights in response to stimulation by input patterns staggered over time such that at the end of learning, the cell’s response favors one input pattern over others to exhibit feature selectivity. In this paper we study the applicability of this cell to form feature specific clusters and show how an array of these cells when connected through an RC-network, interacts diffusively so as to form clusters similar to those observed in cortical ocular dominance maps. Adaptive feature maps is a mechanism by which nature optimize its resources so as to have greater acuity for more abundant features. Neuromorphic feature maps can help design generic machines that can emulate this adaptive behavior.
KeywordsFloating Gate pFET competitive learning WTA Feature maps ocular dominance
- 6.Rahimi, K., Diorio, C., Hernandez, C., Brockhausen, M.D.: A simulation model for floating gate MOS synapse transistors. In: ISCAS (2002)Google Scholar
- 8.Bansal, M., Markan, C.M.: Floating gate Time staggered WTA for feature selectivity. In: Proc. of Workshop on Self-organizing Maps, WSOM 2003, Kitakyushu, Japan (2003)Google Scholar
- 9.Lazzaro, J., Ryckbusch, S., Mahowald, M.A., Mead, C.A.: Winner-take-all Networks of O(N) complexity, NIPS 1 Morgan Kaufman Publishers, San Mateo, CA, pp. 703–711 (1989) Google Scholar
- 10.Kruger, W., Hasler, P., Minch, B., Koch, C.: An adaptive WTA using floating gate technology. In: Advances in NIPS 9, pp. 713–719. MIT Press, Cambridge (1997)Google Scholar