Optical neural networks with unipolar weights

Dickey, Fred M.; DeLaurentis, John M.

doi:10.1016/0030-4018(93)90718-k

Cited by 7 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If we were to store the network weights in the internal variables using only a rescaling constant A, i.e., w = Aγ, then the weights would all have the same sign. Although convergence of the standard backpropagation algorithm is still possible in this case [49], it is usually slower and more difficult, so it is convenient to redefine the variable [11] D → D so that the interval of the internal variable in which Equation ( 11 The new learning algorithm is an adaptation of the backpropagation algorithm, chosen due to its widespread use and robustness. In our case, the activation function of the neurons is the function that relates the output of a node memristor with its input, as seen in Equation (10).…”

Section: Backward Passmentioning

confidence: 99%

Perceptrons from memristors

et al. 2020

View full text Add to dashboard Cite

Memristors, resistors with memory whose outputs depend on the history of their inputs, have been used with success in neuromorphic architectures, particularly as synapses and non-volatile memories. However, to the best of our knowledge, no model for a network in which both the synapses and the neurons are implemented using memristors has been proposed so far. In the present work we introduce models for single and multilayer perceptrons based exclusively on memristors. We adapt the delta rule to the memristor-based single-layer perceptron and the backpropagation algorithm to the memristor-based multilayer perceptron. Our results show that both perform as expected for perceptrons, including satisfying Minsky-Paperts theorem. As a consequence of the Universal Approximation Theorem, they also show that memristors are universal function approximators. By using memristors for both the neurons and the synapses, our models pave the way for novel memristor-based neural network architectures and algorithms. A neural network based on memristors could show advantages in terms of energy conservation and open up possibilities for other learning systems to be adapted to a memristor-based paradigm, both in the classical and quantum learning realms.

show abstract

Section: Backward Passmentioning

confidence: 99%