Nips*91 Vlsi Workshop Summary

Analog VLSI Implementation of Gradient Descent

We describe an analog VLSI implementation of a multi-dimensional gradient estimation and descent technique for minimizing an onchip scalar function fO. The implementation uses noise injection and multiplicative correlation to estimate derivatives, as in [Anderson, Kerns 92]. One intended application of this technique is setting circuit parameters on-chip automatically, rather than manually [Kir...

Extended abstracts of the NIPS*97 Workshop - Can Artificial Cerebellar Models Compete to Control Robots?

How to Work Collaboratively Within the Health System: Workshop Summary and Facilitator Reflection

Effectiveness in health services research requires development of specific knowledge and skills for working in partnership with health system decision-makers. In an initial effort to frame capacity-building activities for researchers, we designed a workshop on working collaboratively within the health system. The workshop, based on recent research exploring health syste...

National Science Foundation Workshop on Future Research Directions in Testing of Electronic Circuits and Systems: executive summary of workshop report

The goals of the meeting were (1) to identify emerging and mature research areas within the VLSI testing field in order to help focus the field on research necessary to develop algorithms and techniques for testing VLSI circuits and systems designed using future technologies, (2) to address issues related to increasing the impact of the VLSI test field on education in electrical and computer en...

Minimising Contrastive Divergence in Noisy, Mixed-mode VLSI Neurons

This paper presents VLSI circuits with continuous-valued probabilistic behaviour realized by injecting noise into each computing unit(neuron). Interconnecting the noisy neurons forms a Continuous Restricted Boltzmann Machine (CRBM), which has shown promising performance in modelling and classifying noisy biomedical data. The Minimising-Contrastive-Divergence learning algorithm for CRBM is also ...