Winner-take-all neural net with memory

Pánkové, J. I.; Radehaus, C.; Wagner, K.

doi:10.1049/el:19900227

Cited by 24 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basis of the winner-take-all circuit is an electrical network [1] , that has the capability of both lateral and global inhibition. Global inhibition is essential to perform the winner-take-all function and can be realized as a special case of this network, obtained by removing all the local couplings between the cells.…”

Section: Wta Neural Networkmentioning

confidence: 99%

Winner-Take-All Neural Network with Massively Optoelectronic Interconnections

Ali¹,

Abdalla²,

Ali³

2009

American J. of Applied Sciences

View full text Add to dashboard Cite

Abstract:The increased interconnection density, bandwidth, nonlocality and fan-out-fan-in offered by optics over conventional electronic technologies make it a very attractive medium for a variety of application particularity in the field of communication system implementation for all types of computing engines is achieved. This is especially true for neural networks in which the demand for communication resources is extremely high. In this study, the implementation of a neural network that exploits an optical interconnect to perform a real task is described. A pnpn semiconductor device has been connected in parallel with a common load resistance for optical switching. When illuminated, only this device with maximum input will turn on. The voltages across the other devices drop and inhibit their switching ability. With suitable biasing, the winning device can be recall at any time. The result shows, a much faster response (<10ns) can be obtained from thyristors made of III-V compound semiconductors, because their carrier lifetime is considerably shorter than in silicon. With III-V photothyristor, it is possible to combine light emission (even lasing) and photothyristor action in the same unit.

show abstract

Section: Wta Neural Networkmentioning

confidence: 99%

Winner-Take-All Neural Network with Massively Optoelectronic Interconnections

Ali¹,

Abdalla²,

Ali³

2009

American J. of Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In (14), we should choose to control the confidence percentage near 100%. For uniformly distributed activations in [0, 1], we can further simplify (14) to become (15) where is treated as a control factor, which could be selected for various applications. In (6), if we replace by , the practical threshold for the HITNET becomes (16) where the practical accelerated factor is given by (17) For other uniformly distributed activations, we can obtain the same conclusion shown as (17).…”

Section: A Convergence Analysismentioning

confidence: 99%

Winner-take-all neural networks using the highest threshold

Yang

Chen²

2000

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

In this paper, we propose a fast winner-take-all (WTA) neural network by dynamically accelerating the mutual inhibition among competitive neurons. The highest-threshold neural network (HITNET) with an accelerated factor is evolved from the general mean-based neural network (GEMNET), which adopts the mean of active neurons as the threshold of mutual inhibition. When the accelerated factor is optimally designed, the ideal HITNET statistically achieves the highest threshold for mutual inhibition. Both theoretical analyzes and simulation results demonstrate that the practical HITNET converges faster than the existing WTA networks for a large number of competitors.

show abstract