J
Joshua Alspector
Researcher at Telcordia Technologies
Publications - 17
Citations - 507
Joshua Alspector is an academic researcher from Telcordia Technologies. The author has contributed to research in topics: Artificial neural network & Competitive learning. The author has an hindex of 10, co-authored 17 publications receiving 500 citations.
Papers
More filters
Patent
Neuromorphic learning networks
Joshua Alspector,Robert B. Allen +1 more
TL;DR: In this paper, a modified Boltzmann algorithm is used to learn a neuron network which achieves learning by means of a modified BN algorithm, which consists of interconnected input, hidden and output layers of neurons, the neurons being "on-off" or threshold electronic symmetrically connected by adjustable-weight synapse pairs.
Proceedings Article
A Parallel Gradient Descent Method for Learning in Analog VLSI Neural Networks
TL;DR: A perturbation technique that measures, not calculates, the gradient, since the technique uses the actual network as a measuring device, errors in modeling neuron activation and synaptic weights do not cause errors in gradient descent.
Book
Performance of a stochastic learning microchip
TL;DR: A test chip in 2 micron CMOS that can perform supervised learning in a manner similar to the Boltzmann machine and demonstrate the capability to do unsupervised competitive learning with it is fabricated.
Proceedings Article
Stochastic Learning Networks and their Electronic Implementation
TL;DR: A family of learning algorithms that operate on a recurrent, symmetrically connected, neuromorphic network that, like the Boltzmann machine, settles in the presence of noise and a version of the supervised learning algorithm for a network with analog activation functions.
Proceedings Article
Experimental Evaluation of Learning in a Neural Microsystem
TL;DR: Learning measurements from a system composed of a cascadable learning chip, data generators and analyzers for training pattern presentation, and an X-windows based software interface are reported.