Ni1000
Jump to navigation
Jump to search
The Ni1000 is an artificial neural network chip developed by Nestor Corporation and Intel, developed in the 1990s. It is Intel's second-generation neural network chip, but the first all-digital chip. The chip is aimed at image analysis applications– containing more than 3 million transistors – and can analyze 40,000 patterns per second.[1] Prototypes running Nestor's OCR software in 1994 were capable of recognizing around 100 handwritten characters per second. The development was funded with money from DARPA and Office of Naval Research.[2]
References
- ^ Baran, Nicholas (March 1994). "Intel and Nestor to Commercialize Neural-Net Chip". Byte. Archived from the original on 1996-12-21. Retrieved 21 October 2022.
- ^ "Intel's Ni1000 chip holds prospect of commercial neural networks". CBROnline archive at techmonitor.ai. 21 February 1993. Retrieved 14 May 2021.
- Intel/Nestor Ni1000 Recognition Accelerator Technical Specification
- Perrone, Michael P.; Cooper, Leon N. (1995). "The Ni1000: High Speed Parallel VLSI for Implementing Multilayer Perceptrons". In Leen, Todd K.; Tesauro, Gerald; Touretzky, David S. (eds.). Advances in Neural Information Processing Systems 7 (PDF). MIT Press. pp. 747–754. ISBN 9780262201049. Retrieved 21 October 2022.
 | This artificial intelligence-related article is a stub. You can help Wikipedia by expanding it. |