A new neural network architecture with associative memory, pruning and order-sensitive learning.

摘要: A new paradigm of neural network architecture is proposed that works as associative memory along with capabilities pruning and order-sensitive learning. The has a composite structure wherein each node the Hopfield by itself. employs an learning technique converges to user-specified stable states without having any spurious states. This based on geometrical energy function. so designed it allows in binary order progressively carries out retrieval. capacity 2n, where n number basic nodes network. are demonstrated experimenting three different application areas, namely Library Database, Protein Structure Database Natural Language Understanding.