On the Computational Power of Winner-Take-All
- 1 November 2000
- journal article
- research article
- Published by MIT Press in Neural Computation
- Vol. 12 (11), 2519-2535
- https://doi.org/10.1162/089976600300014827
Abstract
This article initiates a rigorous theoretical analysis of the computational power of circuits that employ modules for computing winner-take-all. Computational models that involve competitive stages...Keywords
This publication has 11 references indexed in Scilit:
- Analog VLSI circuits for primitive sensory attentionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Computational sensor for visual tracking with attentionIEEE Journal of Solid-State Circuits, 1998
- Dynamics of a Winner-Take-All Neural NetworkNeural Networks, 1996
- K-winners-take-all circuit with O(N) complexityIEEE Transactions on Neural Networks, 1995
- A high-precision VLSI winner-take-all circuit for self-organizing neural networksIEEE Journal of Solid-State Circuits, 1993
- Multilayer feedforward networks with a nonpolynomial activation function can approximate any functionNeural Networks, 1993
- A cortical model of winner-take-all competition via lateral inhibitionNeural Networks, 1992
- The design, fabrication, and test of a new VLSI hybrid analog-digital neural processing elementIEEE Transactions on Neural Networks, 1992
- Current-mode subthreshold MOS circuits for analog VLSI neural systemsIEEE Transactions on Neural Networks, 1991
- Pattern formation, contrast control, and oscillations in the short term memory of shunting on-center off-surround networksBiological Cybernetics, 1975