ML Anthology

WATTLE: A Trainable Gain Analogue VLSI Neural Network

Richard Coggins, Marwan Jabri
NeurIPS 1993 pp. 874-881
/neurips/1993/coggins1993neurips-wattle/

Abstract

This paper describes a low power analogue VLSI neural network called Wattle. Wattle is a 10:6:4 three layer perceptron with multi(cid:173) plying DAC synapses and on chip switched capacitor neurons fabri(cid:173) cated in 1.2um CMOS. The on chip neurons facillitate variable gain per neuron and lower energy/connection than for previous designs. The intended application of this chip is Intra Cardiac Electrogram classification as part of an implantable pacemaker / defibrillator sys(cid:173) tem. Measurements of t.he chip indicate that 10pJ per connection is achievable as part of an integrated system. Wattle has been suc(cid:173) cessfully trained in loop on parity 4 and ICEG morphology classi(cid:173) fication problems.

PDF NeurIPS Semantic Scholar

Cite

Text

Coggins and Jabri. "WATTLE: A Trainable Gain Analogue VLSI Neural Network." Neural Information Processing Systems, 1993.

Markdown

[Coggins and Jabri. "WATTLE: A Trainable Gain Analogue VLSI Neural Network." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/coggins1993neurips-wattle/)

BibTeX

@inproceedings{coggins1993neurips-wattle,
  title     = {{WATTLE: A Trainable Gain Analogue VLSI Neural Network}},
  author    = {Coggins, Richard and Jabri, Marwan},
  booktitle = {Neural Information Processing Systems},
  year      = {1993},
  pages     = {874-881},
  url       = {https://mlanthology.org/neurips/1993/coggins1993neurips-wattle/}
}