Critical periods and catastrophic interference effects in the development of self-organizing feature maps.

39 citations recorded by the source corpus.

How researchers see this paper

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

Continual Lifelong Learning with Neural Networks: A Review (2018, methodology): “ist models (Thomas and Johnson, 2006; Richardson and Thomas, 2008), in particular with the use of self-organizing learning systems which reduce the levels of functional plasticity through a two-phase training of the topographic neural map (Kohonen, 1982, 1995; Miikkulainen, 1997).”
Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, background): “On the other hand, unsupervised approaches (e.g., Parisi et al., 2017; Richardson and Thomas, 2008) do not typically take into account task-relevant signals or modulatory feedback which are crucial for stabilizing and tuning internal representations driven by bottom-up sensory observations (Zenke et”
Lifelong learning of human actions with deep neural network self-organization (2017, background): “Specifically for self-organizing networks, catastrophic interference is modulated by the conditions of map plasticity, the available resources to represent information, and the similarity between new and old knowledge (Richardson & Thomas, 2008).”
Online Continual Learning on Sequences (2020, background): “Specifically for self-organizing networks, catastrophic interference is modulated by the conditions of map plasticity, the available resources to represent information, and the similarity between new and old knowledge [64, 70].”