Opposition-Based Learning: A New Scheme for Machine Intelligence

Opposition-based learning as a new scheme for machine intelligence is introduced. Estimates and counter-estimates, weights and opposite weights, and actions versus counter-actions are the foundation of this new approach. Examples are provided. Possibilities for extensions of existing learning algorithms are discussed. Preliminary results are provided.

• Type: Conference
• Year: 2005
• Where: CIMCA
• Authors: Hamid R. Tizhoosh
• Keywords: Actions Versus Counter-actions, CIMCA 2005, Opposite Weights, Opposition-based Learning