A hypercube compact neural network
A major problem facing implementation of neural networks is the connection problem. One popular tradeoff is to remove connections. Random disconnection severely degrades the capabilities. The hypercube based Compact Neural Network (CNN) has structured architecture combined with a rearrangement of the memory vectors gives a larger input space and better degradation than a cost equivalent network with more connections. The CNNs are based on a Hopfield network. The changes from the Hopfield net include states of -1 and +1 and when a node was evaluated to 0, it was not biased either positive or negative, instead it resumed its previous state. L = PEs, N = memories and t/sub ij/s is the weights between i and j.
- Research Organization:
- Dept. of Electrical Engineering, Univ. of Washington, Seattle, WA (US)
- OSTI ID:
- 6024078
- Report Number(s):
- CONF-8809132-
- Journal Information:
- Neural Networks; (United States), Vol. 1:1; Conference: 1. International Neural Network Society annual meeting, Boston, MA, USA, 6 Sep 1988
- Country of Publication:
- United States
- Language:
- English
Similar Records
Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data
A fully digital architecture for multi-state neural networks
Related Subjects
HYPERCUBE COMPUTERS
COMPUTER NETWORKS
ALGORITHMS
COMPUTER ARCHITECTURE
COMPUTERIZED SIMULATION
IMPLEMENTATION
INTEGRATED CIRCUITS
MEMORY DEVICES
PERFORMANCE
SILICON
VECTOR PROCESSING
COMPUTERS
ELECTRONIC CIRCUITS
ELEMENTS
MATHEMATICAL LOGIC
MICROELECTRONIC CIRCUITS
PROGRAMMING
SEMIMETALS
SIMULATION
990210* - Supercomputers- (1987-1989)