Digital Boltzmann VLSI for constraint satisfaction and learning
Murray, Michael, Leung, Ming-Tak, Boonyanit, Kan, Kritayakirana, Kong, Burg, James B., Wolff, Gregory J., Watanabe, Tokahiro, Schwartz, Edward, Stork, David G., Peterson, Allen M.
–Neural Information Processing Systems
We built a high-speed, digital mean-field Boltzmann chip and SBus board for general problems in constraint satjsfaction and learning. Each chip has 32 neural processors and 4 weight update processors, supporting an arbitrary topology of up to 160 functional neurons. On-chip learning is at a theoretical maximum rate of 3.5 x 10
Neural Information Processing Systems
Dec-31-1994
- Country:
- North America
- United States
- New York (0.04)
- California
- Alameda County > Berkeley (0.04)
- Santa Clara County
- Stanford (0.04)
- Mountain View (0.04)
- San Mateo County
- San Mateo (0.04)
- Menlo Park (0.04)
- Trinidad and Tobago > Trinidad
- United States
- North America
- Industry:
- Semiconductors & Electronics (0.69)
- Technology: