ML Anthology

Generic Analog Neural Computation - The EPSILON Chip

Stephen Churcher, Donald J. Baxter, Alister Hamilton, Alan F. Murray, H. Martin Reekie
NeurIPS 1992 pp. 773-780
/neurips/1992/churcher1992neurips-generic/

Abstract

An analog CMOS VLSI neural processing chip has been designed and fabri(cid:173) cated. The device employs "pulse-stream" neural state signalljng, and is capa(cid:173) ble of computing some 360 million synaptic connections per secood. In addi(cid:173) tion to basic characterisation results. the performance of the chip in solving "real-world" problems is also demonstrated.

PDF NeurIPS Semantic Scholar

Cite

Text

Churcher et al. "Generic Analog Neural Computation - The EPSILON Chip." Neural Information Processing Systems, 1992.

Markdown

[Churcher et al. "Generic Analog Neural Computation - The EPSILON Chip." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/churcher1992neurips-generic/)

BibTeX

@inproceedings{churcher1992neurips-generic,
  title     = {{Generic Analog Neural Computation - The EPSILON Chip}},
  author    = {Churcher, Stephen and Baxter, Donald J. and Hamilton, Alister and Murray, Alan F. and Reekie, H. Martin},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {773-780},
  url       = {https://mlanthology.org/neurips/1992/churcher1992neurips-generic/}
}