Are analog neural networks better than binary neural networks?
From MaRDI portal
Publication:1126906
DOI10.1007/BF01202855zbMath0902.68165MaRDI QIDQ1126906
Publication date: 9 August 1998
Published in: Circuits, Systems, and Signal Processing (Search for Journal in Brave)
68T05: Learning and adaptive systems in artificial intelligence
Cites Work
- Unnamed Item
- A new polynomial-time algorithm for linear programming
- ``Neural computation of decisions in optimization problems
- Decreasing energy functions as a tool for studying threshold networks
- Simple Local Search Problems that are Hard to Solve
- A generalized convergence theorem for neural networks
- On the analysis of dynamic feedback neural nets
- Neural networks, error-correcting codes, and polynomials over the binary n-cube
- Minimum-seeking properties of analog neural networks with multilinear objective functions
- Neural networks and physical systems with emergent collective computational abilities.
- Neurons with graded response have collective computational properties like those of two-state neurons.