Characterization of Analog Local Cluster Neural Network Hardware for Control

Sitte, Joaquin; Zhang, Liang; Rueckert, Ulrich

doi:10.1109/tnn.2007.899518

Cited by 2 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the common approaches for analog neuromorphic systems is to utilize circuitry that operates in subthreshold mode, typically for power efficiency purposes [101], [325], [330], [334], [373], [576], [577], [641], [647], [654], [665], [684], [700], [704], [704], [720], [721], [727], [737], [1045], [1079], [1080], [1084], [1089], [1160]- [1163], [1274], [1394], [1411], [1596]- [1619]. In fact, the original neuromorphic definition by Carver Mead referred to analog circuits that operated in subthreshold mode [1].…”

Section: A High-levelmentioning

confidence: 99%

“…Control tasks have been popular for neuromorphic systems because they typically require real-time performance, are often deployed in real systems that require small volume and low power, and have a temporal processing component, so they benefit from models that utilize recurrent connections or delays on synapses. A large variety of different control applications have utilized neuromorphic systems [466], [687], [688], [863], [872], [895], [902], [903], [920], [932], [962], [1017], [1051], [1085], [1660], [2561], [2562], but by far the most common control test case is the cart-pole problem or the inverted pendulum task [487], [512], [792], [902], [903], [1008], [1045], [1337], [1340], [2563]. Neuromorphic systems have also been applied to video games, such as Pong [1563], PACMAN [2405], and Flappy Bird [1337].…”

Section: Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

171

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: A High-levelmentioning

confidence: 99%

Section: Applicationsmentioning

confidence: 99%

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

171

180

View full text Add to dashboard Cite

show abstract

“…Since most of the conventional clustering algorithms are based on only the mean values of the observations, the clustering results are sometimes inadequate for clustering probabilistic data. For deterministic data, conventional clustering algorithms including fuzzy -means algorithm have been widely used [16], [17]. The proposed clustering algorithm utilizes both the mean and the covariance information of GPDFs and thereby produces very promising clustering results.…”

Section: Introductionmentioning

confidence: 99%

Centroid Neural Network With a Divergence Measure for GPDF Data Clustering

Park

Kwon

Chung

2008

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

An unsupervised competitive neural network for efficient clustering of Gaussian probability density function (GPDF) data of continuous density hidden Markov models (CDHMMs) is proposed in this paper. The proposed unsupervised competitive neural network, called the divergence-based centroid neural network (DCNN), employs the divergence measure as its distance measure and utilizes the statistical characteristics of observation densities in the HMM for speech recognition problems. While the conventional clustering algorithms used for the vector quantization (VQ) codebook design utilize only the mean values of the observation densities in the HMM, the proposed DCNN utilizes both the mean and the covariance values. When compared with other conventional unsupervised neural networks, the DCNN successfully allocates more code vectors to the regions where GPDF data are densely distributed while it allocates fewer code vectors to the regions where GPDF data are sparsely distributed. When applied to Korean monophone recognition problems as a tool to reduce the size of the codebook, the DCNN reduced the number of GPDFs used for code vectors by 65.3% while preserving recognition accuracy. Experimental results with a divergence-based k-means algorithm and a divergence-based self-organizing map algorithm are also presented in this paper for a performance comparison.

show abstract

Characterization of Analog Local Cluster Neural Network Hardware for Control

Cited by 2 publications

References 15 publications

A Survey of Neuromorphic Computing and Neural Networks in Hardware

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Centroid Neural Network With a Divergence Measure for GPDF Data Clustering

Contact Info

Product

Resources

About