Scalable Closed-Boundary Analog Neural Networks

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

doi:10.1109/tnn.2004.824415

Cited by 13 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probabilistic neural networks, yet another special-case of feed-forward neural networks that have a particular type of functionality that is related to Bayesian calculations, have several neuromorphic implementations [1035]- [1043]. Singlelayer feed-forward networks that utilize radial basis functions as the activation function of the neurons have also been used in neuromorphic implementations [530], [747], [825], [826], [1044]- [1053]. In recent years, with the rise of deep learning, convolutional neural networks have also seen several implementations in neuromorphic systems [1054]- [1075].…”

Section: Network Modelsmentioning

confidence: 99%

“…For example, synaptic weights are frequently stored in digital memory for analog neuromorphic systems. Other neuromorphic platforms are primarily analog, but utilize digital communication, either within the chip itself, to and from the chip, or between neuromorphic chips [13], [133], [406], [412], [413], [415], [417]- [421], [424], [429], [434]- [437], [446]- [449], [452]- [455], [468]- [470], [472], [480], [586], [615], [616], [813], [826], [827], [829], [854], [855], [1024], [1108], [1109], [1133], [1134], [1171], [1172], [1198], [1221], [1276], [1372], [1452], [1453], [1761]- [1776]. Communication within and between neuromorphic chips is usually in the form of digital spikes for these implementations.…”

Section: A High-levelmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

172

180

View full text Add to dashboard Cite

Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture. This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine learning problems. The promise of the technology is to create a brainlike ability to learn and adapt, but the technical challenges are significant, starting with an accurate neuroscience model of how the brain works, to finding materials and engineering breakthroughs to build devices to support these models, to creating a programming framework so the systems can learn, to creating applications with brain-like capabilities. In this work, we provide a comprehensive survey of the research and motivations for neuromorphic computing over its history. We begin with a 35-year review of the motivations and drivers of neuromorphic computing, then look at the major research areas of the field, which we define as neuro-inspired models, algorithms and learning approaches, hardware and devices, supporting systems, and finally applications. We conclude with a broad discussion on the major research topics that need to be addressed in the coming years to see the promise of neuromorphic computing fulfilled. The goals of this work are to provide an exhaustive review of the research conducted in neuromorphic computing since the inception of the term, and to motivate further work by illuminating gaps in the field where new research is needed.

show abstract

Section: Network Modelsmentioning

confidence: 99%

Section: A High-levelmentioning

confidence: 99%

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

172

180

View full text Add to dashboard Cite

show abstract

“…Hardware realization of NNs is an interesting issue [4], [5]. There are many approaches to implement NNs [6], [7].…”

Section: Introductionmentioning

confidence: 99%

Simultaneous Perturbation Learning Rule for Recurrent Neural Networks and Its FPGA Implementation

Maeda

Wakamura

2005

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Recurrent neural networks have interesting properties and can handle dynamic information processing unlike ordinary feedforward neural networks. However, they are generally difficult to use because there is no convenient learning scheme. In this paper, a recursive learning scheme for recurrent neural networks using the simultaneous perturbation method is described. The detailed procedure of the scheme for recurrent neural networks is explained. Unlike ordinary correlation learning, this method is applicable to analog learning and the learning of oscillatory solutions of recurrent neural networks. Moreover, as a typical example of recurrent neural networks, we consider the hardware implementation of Hopfield neural networks using a field-programmable gate array (FPGA). The details of the implementation are described. Two examples of a Hopfield neural network system for analog and oscillatory targets are shown. These results show that the learning scheme proposed here is feasible.

show abstract