Generalized Artificial Neural Networks (GANNs)

Fakhraie, S.M.; Smith, K.C.

doi:10.1007/978-1-4615-6311-2_3

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our theoretical investigations and simulations have proven that a network composed of neurons with sigmoid activation functions interconnected with single-transistor synaptic blocks can be used successfully in the implementation of feedforward-multilayer perceptron networks [2]. As will become clear below, the intrinsic MOS characteristics of I = k.(V-V,,,)' provides the basis for these new architectures.…”

Section: Introductionmentioning

confidence: 88%

“…A training algorithm, employing a modified version of error back-propagation, has been developed [2], and, for each case, proper training equations have been derived Using this simulator. we have examined many different network compositions and have compared their performances based on criteria such as convergence of the training algorithm, stability, running time, number of iterations to achieve an acceptable solution, hardware complexity, number of interconnects, and achievable low and high output levels with the same number of hidden units.…”

Section: Simulationsmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of three different architectures for MOS-compatible quadratic synapses

Fakhraie¹,

Smith²,

Xu³

Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks

View full text Add to dashboard Cite

Inspired by the harmony between the basic functional elements of biological neural networks and their natural operating media, we have been seeking for ways to implement Artificial Neural Networks ( A N N s ) using the intrinsic functionality of the most commonly available devices in an electronics technology, in contrast to the method of hardware-compilation of softwaresimulation modules. In the case of MOS technology, we employ a quadratic functional equation similar to that found in standard MOS transistors to implement synapses in ANNs. A structure has been proposed in [3] to implement a MOS device with extemally-controllable threshold voltage to be employed as a synapse. In the present work, we develop and compare practical architectures within which these synapses can be utilized optimally. A simulator and proper training algorithms have been developed to simulate different hardware-based architectures.

show abstract

Section: Introductionmentioning

confidence: 88%

Section: Simulationsmentioning

confidence: 99%

Comparison of three different architectures for MOS-compatible quadratic synapses

Fakhraie¹,

Smith²,

Xu³

Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks

View full text Add to dashboard Cite

show abstract

Scalable Closed-Boundary Analog Neural Networks

Fakhraie

Farshbaf

Smith³

2004

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

In many pattern-classification and recognition problems, separation of different swarms of class representatives is necessary. As well, in function-approximation problems, neurons with a local area of influence have demonstrated measurable success. In our previous work, we have shown how intrinsic quadratic characteristics of traditional metal-oxide-semiconductor (MOS) devices can be used to implement hyperspherical discriminating surfaces in hardware-implemented neurons. In this work, we further extend the concept from quadratic forms to more-arbitrary closed-boundary shapes. Accordingly, we demonstrate how intrinsic characteristics of submicron MOS devices can be utilized to implement efficient pattern discriminators for various applications and, through representative simulations, show their success in some typical function-approximation problems. Further, we offer two mathematical interpretations of possible roles for these networks: Geometrically, we show that our networks employ closed hypercone shapes as their discriminating surfaces; analytically, we show that a set of these synapses connected to a common integrating body calculates the distance between their inputs and weight vectors using a power norm. The feasibility of the idea is practically investigated by design, implementation, and test of a three-dimensional (3-D) closed-boundary pattern classifier, fabricated in 0.35-microm complimentary MOS, whose results are reflected in this work.

show abstract

Generalized Artificial Neural Networks (GANNs)

Cited by 2 publications

References 10 publications

Comparison of three different architectures for MOS-compatible quadratic synapses

Comparison of three different architectures for MOS-compatible quadratic synapses

Scalable Closed-Boundary Analog Neural Networks

Contact Info

Product

Resources

About