Winner-Take-All Networks with Lateral Excitation
The analog VLSI current mode winner-take-all (WTA) circuit, originally presented in  is a good example of a very well designed architecture. It is able to process globally all the signals of an input array, it uses a very limited amount of transistors per input node and it operates in parallel, with strictly local interconnections. This architecture has been extensively and successfully used in a wide variety of applications [3, 6, 7]. More recently, interesting modifications to the original circuit have been proposed in  and . In both cases, the authors added to each element of the WTA network a local feedback circuit to obtain a hysteretic behavior in the selection/de-selection of the winning node: every time a new winner is selected the local feedback circuit adds a constant bias current to its input. The circuit will then de-select the winner when either its input current becomes lower than other inputs by a factor greater than the bias current or when the whole network is reset. From a functional point of view, this operation enhances the resolution of the network and eliminates instability problems, providing a robust mechanism that withstands the selection of other potential winners unless they are stronger than the selected one by a set amount. The authors of  proposed a scheme for distributing locally the hysteretic component so that the winning input would be able to shift between adjacent locations maintaining its winning status, without having to reset the network.
KeywordsGate Voltage Input Current Neural Information Processing System Lateral Excitation Diffusor Network
Unable to display preview. Download preview PDF.
- K. A. Boahen and A. G. Andreou. A contrast sensitive silicon retina with reciprocal synapses. Advances in Neural Information Processing Systems, 4:764–772, 1992.Google Scholar
- S. P. DeWeerth and T. G. Morris. Analog VLSI circuits for primitive sensory attention. In Proceedings of the IEEE International Symposium on Circuits and Systems, volume 6, pages 507–510, 1994.Google Scholar
- J. Lazzaro, S. Ryckebusch, M. A. Mahowald, and C. A. Mead. Winner-take-all networks of O(n) complexity. In D.S. Touretzky, editor, Advances in neural information processing systems, volume 2, pages 703–711, San Mateo-CA, 1989. Morgan Kaufmann.Google Scholar
- S. Liu and K. Boahen. Adaptive retina with center-surround receptive field. In D.S. Touretzky, M.C. Mozer, and M.E. Hasselmo, editors, Advances in neural information processing systems, volume 8. MIT Press, 1996.Google Scholar
- E. Niebur and C. Koch. Control of selective visual attention: modeling the “where” pathway. In D.S. Touretzky, M.C. Mozer, and M.E. Hasselmo, editors, Advances in neural information processing systems, volume 8. MIT Press, 1996.Google Scholar