Proceedings Article10.1109/ICASSP.1990.116058
RAP: a ring array processor for multilayer perceptron applications
Nelson Morgan,James Beck,Eric Allman,J. Beer +3 more
- 03 Apr 1990
- pp 1005-1008
5
TL;DR: Initial tests with the new hardware have confirmed the major assumptions of the estimates from the simulations, and the RAP is a multiprocessor system which is particularly targeted in the training of feedforward networks for the recognition of continuous speech.
read more
Abstract: A ring array processor (RAP) designed for fast simulation of artificial neural network algorithms is described. The RAP is a multiprocessor system which is particularly targeted in the training of feedforward networks for the recognition of continuous speech. The overall system consists of several four-processor boards serving together as an array processor for a 68020-based host running a real-time operating system. The prototype design includes 64 Mbytes of dynamic memory (expandable to 256) and 4 Mbytes of fast static RAM distributed between 16 processors on four boards. Theoretical peak performance is 512 MFLOPS, and simulations have indicated a sustained throughput of roughly half of this for algorithms of current interest, including communication overhead of roughly 10-30%. Initial tests with the new hardware have confirmed the major assumptions of the estimates from the simulations. >
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Deep learning for AI
TL;DR: In this paper, neural networks are used to learn the rich internal representations required for difficult tasks such as recognizing objects or understanding language, which can be used to classify objects or understand language.
577
Patent
Neural networks with learning and expression capability
Robert George Hercus
- 21 Jun 2004
TL;DR: A neural network comprising a plurality of neurons in which any one of the neurons in the plurality is able to associate with itself or another neuron in a plurality via active connections to a further neuron in the neural network is defined in this paper.
28
SPERT: a VLIW/SIMD microprocessor for artificial neural network computations
Krste Asanovic,James Beck,Brian Kingsbury,Phil Kohn,Nelson Morgan,John Wawrzynek +5 more
- 04 Aug 1992
TL;DR: SPERT (synthetic perceptron testbed) is a fully programmable single chip microprocessor designed for efficient execution of artificial neural network algorithms that represents over an order of magnitude reduction in cost for problems where fixed-point arithmetic is satisfactory.
22
Digital neural emulators using tree accumulation and communication structures
TL;DR: The feasibility and characteristics of the proposed configurations to emulate single and/or multiple neural networks simultaneously are discussed, and a comparison with recently proposed neurocomputer architectures is reported.
17
Using simulations of reduced precision arithmetic to design a neuro-microprocessor
Krste Asanovic,Nelson Morgan,John Wawrzynek +2 more
- 01 Jun 1993
TL;DR: This study shows that back-propagation training algorithms only require moderate precision, and shows that 16b weight values and 8b output values are sufficient to achieve training and classification results comparable to 32b floating point.
References
Learning internal representations by error propagation
David E. Rumelhart,Geoffrey E. Hinton,Ronald J. Williams +2 more
- 01 Jan 1988
TL;DR: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
•Book
Learning internal representations by error propagation
David E. Rumelhart,Geoffrey E. Hinton,Ronald J. Williams +2 more
- 03 Jan 1986
TL;DR: In this paper, the problem of the generalized delta rule is discussed and the Generalized Delta Rule is applied to the simulation results of simulation results in terms of the generalized delta rule.
16K
•Proceedings Article
Optimal Brain Damage
Yann LeCun,John S. Denker,Sara A. Solla +2 more
- 01 Jan 1989
TL;DR: A class of practical and nearly optimal schemes for adapting the size of a neural network by using second-derivative information to make a tradeoff between network complexity and training set error is derived.
Continuous speech recognition using multilayer perceptrons with hidden Markov models
Nelson Morgan,Hervé Bourlard +1 more
- 03 Apr 1990
TL;DR: A phoneme based, speaker-dependent continuous-speech recognition system embedding a multilayer perceptron (MLP) into a hidden Markov model (HMM) approach is described, which appears to be somewhat better when MLP methods are used to estimate the probabilities.
212
A unified systolic architecture for artificial neural networks
Sun-Yuan Kung,Jenq-Neng Hwang +1 more
TL;DR: A unified formulation is provided for both the retrieving and the learning phases of most ANNs, and on the basis of the formulation, a programmable ring systolic array is developed that maximizes the strength of VLSI in terms of intensive and pipelined computing and yet circumvents the limitation on communication.
130