Networks with recurrent connection weights that reflect the covariation between pattern elements can dynamically recall patterns and simulate certain forms of memory.
4.1 The Four Hebbian Learning Rules for Neural Networks
4.2 Simulating Memory Recall Using Recurrent Auto-Associator Networks
4.3 Recalling Distinct Memories Using Negative Connections in Auto-Associators
4.4 Synchronous versus Asynchronous Updating in Recurrent Auto-Associators
4.5 Graceful Degradation and Simulated Forgetting
4.6 Simulating Storage and Recall of a Sequence of Patterns
4.7 Hebbian Learning, Recurrent Auto-Association and Models of Hippocampus
Researchers should cite this work as follows:
Thomas J. Anastasio (2013), "[Illinois] MCB 493 Lecture 4: Covariation Learning and Auto-Associative Memory," http://nanohub.org/resources/16950.
University of Illinois at Urbana-Champaign, Urbana, IL