A novel technology for fabricating customizable VLSI artificial neural network chips
Conference
·
OSTI ID:10190097
- Lawrence Livermore National Lab., CA (United States)
- Naval Air Warfare Center, China Lake, CA (United States)
This paper describes an implementation of hardware neural networks using highly linear thin-film resistor technology and an 8-bit binary weight circuit to produce customizable artificial neural network chips and systems. These neural networks are programmed using precision laser cutting and deposition. The fast turnaround of laser-based customization allows us to explore different neural network architectures and to rapidly program the synaptic weights. Our customizable chip allows us to expand an artificial network laterally and vertically. This flexibility permits us to build very large neural network systems.
- Research Organization:
- Lawrence Livermore National Lab., CA (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 10190097
- Report Number(s):
- UCRL-JC-109597; CONF-9206102-6; ON: DE94000398
- Resource Relation:
- Conference: International joint conference on neural networks,Baltimore, MD (United States),7-11 Jun 1992; Other Information: PBD: 5 Feb 1992
- Country of Publication:
- United States
- Language:
- English
Similar Records
Customizable VLSI artificial neural network chips based on a novel technology
A programmable analog neural network processor
Neural network chips for trigger purposes in high energy physics
Conference
·
Tue Sep 14 00:00:00 EDT 1993
·
OSTI ID:10190097
+1 more
A programmable analog neural network processor
Journal Article
·
Fri Mar 01 00:00:00 EST 1991
· IEEE Transactions on Neural Networks (Institute of Electrical and Electronics Engineers); (United States)
·
OSTI ID:10190097
Neural network chips for trigger purposes in high energy physics
Conference
·
Tue Dec 31 00:00:00 EST 1996
·
OSTI ID:10190097