Biased ART: A neural architecture that shifts attention toward previously disregarded features following an incorrect prediction
By Gail A. Carpenter, Chaitanya Sai Gaddam. 2010
38 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Cognitive Neuroscience, Statistical and Nonlinear Physics
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
- Tyler L. Hayes
- Christopher Kanan
- Vincenzo Lomonaco
- Nathan D. Cahill
- Ronald Kemker
- Davide Maltoni
- Stephen Grossberg
- Kushal Kafle
In Cognitive Neuroscience
- Tyler L. Hayes
- Christopher Kanan
- Stephen Grossberg
- Nathan D. Cahill
- Ronald Kemker
- Ali Ayub
- Alan R. Wagner
- Vincenzo Lomonaco
In Statistical and Nonlinear Physics
Citations in the corpus
- Memory Efficient Experience Replay for Streaming Learning (2018, background): “ARTMAP networks [11], [12], [13], [71] are another approach and they learn faster.”
- Adaptive Resonance Theory: How a brain learns to consciously attend, learn, and recognize a changing world (2013, background): “…learning ‘‘in school’’ can lead to effective knowledge acquisition later on by unsupervised learning ‘‘in the real world’’ (Amis & Carpenter, 2009); and Biased ART, which shows how attention can be selectively diverted from features that cause predictive errors (Carpenter & Gaddam, 2010).”
- New Metrics and Experimental Paradigms for Continual Learning (2018, methodology): “We evaluated four continual learning algorithms: Incremental 1-Nearest Neighbor (1NN), biased ARTMAP (bARTMAP) [1], GeppNet [5], and an online multi-layer perceptron (MLP) by comparing them to a small offline MLP neural network.”