Localist Attractor Networks

By Richard S. Zemel, Michael C. Mozer. 2001

34 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Model Architectures, Neuroscience

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. Bernt Schiele
2. Yoshua Bengio
3. J. Urgen Schmidhuber
4. Mohit Bansal
5. Sergey Levine
6. Trevor Darrell
7. Quoc V. Le
8. Ruslan Salakhutdinov

In Cognitive Neuroscience

1. J. Urgen Schmidhuber
2. Sjoerd van Steenkiste
3. Klaus Greff
4. Hava T. Siegelmann
5. Dimitri Nowicki
6. Bernt Schiele
7. Hilde Kuehne
8. Anna Kukleva

In Model Architectures

1. Klaus Greff
2. Sjoerd van Steenkiste
3. Bernt Schiele
4. J. Urgen Schmidhuber
5. Hava T. Siegelmann
6. Richard S. Zemel
7. Mengye Ren
8. Dimitri Nowicki

In Neuroscience

1. Hava T. Siegelmann
2. Dimitri Nowicki
3. Anna Kukleva
4. Hilde Kuehne
5. Bernt Schiele
6. Michael C. Mozer
7. J. Urgen Schmidhuber
8. Richard S. Zemel

Citations in the corpus

• On the Binding Problem in Artificial Neural Networks (2020, background): “Localist attractor networks (Zemel and Mozer, 2001) and flexible kernel memory (Nowicki and Siegelmann, 2010) are two approaches that address this issue by introducing a separate representation for each attractor.”
• Recent Advances of Continual Learning in Computer Vision: An Overview (2021, neutral): “They proposed a method called Attention At-tractor Network which adds an additional penalty term, adapted from attractor networks [37], to the loss function.”
• Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting (2021, positive): “[37] propose to use an attention attractor network [54] to regularize the learning of novel classes with respect to accumulated base attractor vectors.”
• A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification (2020, background): “, 2019): Inspired by the attractor networks (Zemel and Mozer, 2001), the attention attractor network model which regularizes the learning of novel classes is designed for incremental few-shot learning on image classification task.”
• Incremental Few-Shot Learning with Attention Attractor Networks (2018, background): “Our proposed regularizer is inspired by attractor networks [42] and can be thought of as a memory of the base classes, adapted to the new classes.”
• Convolutional Bipartite Attractor Networks (2019, background): “The problem of interpretation is well matched to an early and often overlooked architecture, the attractor net [12, 13, 19, 46].”
• Flexible Kernel Memory (2010, methodology): “Current implementation of our memory is based on a simple competitive clustering algorithm and consolidates memories in a spirit similar to the localist attractor networks [43].”