A stochastic architecture for neural nets

Bout, Van den; Miller, '

doi:10.1109/icnn.1988.23882

Cited by 10 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the kth hidden layer, E(rhz3) and Var(&,) can be described by (7) and (8) . Var(h,,) is nonzero in the kth hidden layer when k 2 2 because the first inputs in the input layer and a1 M 0.035. term in the right side of (8) is nonzero due to the random noise…”

Section: Synaptic Multiplication and Logical Oring In The Kth Hiddmentioning

confidence: 99%

See 1 more Smart Citation

Architecture and statistical model of a pulse-mode digital multilayer neural network

Kim

Shanblatt²

1995

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

A new architecture and a statistical model for a pulse-mode digital multilayer neural network (DMNN) are presented. Algebraic neural operations are replaced by stochastic processes using pseudo-random pulse sequences. Synaptic weights and neuron states are represented as probabilities and estimated as average rates of pulse occurrences in corresponding pulse sequences. A statistical model of error (or noise) is developed to estimate relative accuracy associated with stochastic computing in terms of mean and variance. The stochastic computing technique is implemented with simple logic gates as basic computing elements leading to a high neuron-density on a chip. Furthermore, the use of simple logic gates for neural operations, the pulse-mode signal representation, and the modular design techniques lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Any size of a feedforward network can be configured where processing speed is independent of the network size. Multilayer feedforward networks are modeled and applied to pattern classification problems such as encoding and character recognition.

show abstract

Section: Synaptic Multiplication and Logical Oring In The Kth Hiddmentioning

confidence: 99%

“…Since Var(Cj) = Var(2i',j) = 0 from (5) when n = P, = N , Var(riZ,,) = 0 in(8). This deterministic nature of the synaptic multiplications in the first hidden layer contributes to the high accuracy of the stochastic computing technique.Before developing the statistic model of an n-input logical OR, the model for a two-input OR is developed first.…”

mentioning

confidence: 99%