Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning

By Randall C. O’Reilly. 2001

158 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Andrew Kyle Lampinen
2. Felix Hill
3. Michael J Frank
4. James L. McClelland
5. Adam Santoro
6. Matthew Botvinick
7. Luke S. Zettlemoyer
8. Yoshua Bengio

In Cognitive Neuroscience

1. Michael J Frank
2. Matthew Botvinick
3. Randall C. O’Reilly
4. Thomas E. Hazy
5. Eric D. Claus
6. James L. McClelland
7. J. Cohen
8. Andrew Kyle Lampinen

In Model Architectures

1. Michael J Frank
2. Eric D. Claus
3. Robert L. Goldstone
4. Ji Yeon Son
5. Thomas E. Hazy
6. Randall C. O’Reilly
7. Stephen Clark
8. R. Schneider

Citations in the corpus

• Environmental drivers of systematicity and generalization in a situated agent (2019, background): “Note that systematic generalisation is also sometimes referred to as ‘combinatorial generalisation’ (O’Reilly, 2001; Battaglia et al., 2018).”
• Banishing the homunculus: making working memory work. (2006, background): “…been observed for example in electrophysiological studies of working In the 1-2 extension of the AX-CPT task (1-2-AX; Figure 2; Frank, Loughry, & O'Reilly, 2001; Kroger, Nystrom, O'Reilly, Noelle, Braver, & Cohen, in preparation), the target sequence varies depending on prior task demand stimuli…”
• Anatomy of a decision: striato-orbitofrontal interactions in reinforcement learning, decision making, and reversal. (2006, methodology): “The model is implemented using a subset of the Leabra framework (O’Reilly & Munakata, 2000; O’Reilly, 2001).”
• Hold your horses: A dynamic computational role for the subthalamic nucleus in decision making (2006, unknown): “The model is implemented using the Leabra framework (O’Reilly, 2001; O’Reilly & Munakata, 2000).”
• The Transfer of Scientific Principles Using Concrete and Idealized Simulations (2005, background): “Parts that start out homogeneous and undifferentiated can each become specialized as a result of interactions between the parts (O’Reilly, 2001).”
• Recurrent Processing during Object Recognition (2013, background): “small errors in processing can become magnified over the course of repeated recurrent interactions (O’Reilly, 2001).”