Learning and Categorization in Modular Neural Networks

By J. Murre. 1992

How researchers see this paper

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

In Model Architectures

Citations in the corpus

Measuring Catastrophic Forgetting in Neural Networks (2017, background): “To learn new data, CALM searches among competing nodes to see which nodes have not been committed to another representation (Murre 2014).”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “evertheless be evolved in computer simulations (Bullinaria, 2007b, 2009b). One seminal early study by Happel and Murre (1994) proposed the evolutionary design of modular neural networks, called CALM (Murre, 1992), in which modules could perform unsupervised learning, and the intermodule connectivity”
Structural Synaptic Plasticity Has High Memory Capacity and Can Explain Graded Amnesia, Catastrophic Forgetting, and the Spacing Effect (2014, background): “Such approaches include ART-type architectures [90], emergent category-specific modularity [93], hard-wired modularity [94], and also ideas involving grandmother cells [95] or, in technical terms, look-up-tables [16].”
Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference (2018, methodology): “Experience replay (Lin, 1992; Murre, 1992) is an old technique that remains a central component of deep learning systems attempting to learn in non-stationary settings, and we will adopt here conventions from recent work (Zhang & Sutton, 2017; Riemer et al.”
Scalable Recollections for Continual Lifelong Learning (2017, background): “2017; Rebuffi, Kolesnikov, and Lampert 2017; Lopez-Paz and Ranzato 2017) were also some of the earliest solutions to the catastrophic forgetting problem in the supervised learning setting (Murre 1992; Robins 1995).”
Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning (2017, neutral): “One popular approach for addressing this problem is rehearsals (Murre, 1992), (Robins, 1995).”
The consolidation of learning during sleep: comparing the pseudorehearsal and unlearning accounts (1999, unknown): “Rehearsal was first explored in the context of catastrophic forgetting by Hetherington and Seidenberg ( 1989 ) and Ratcliff ( 1990 ) , and a range of rehearsal methods have been explored by Murre ( 1992a ) ; Robins ( 1995 ) .”
Catastrophic Forgetting and the Pseudorehearsal Solution in Hopfield-type Networks (1998, methodology): “Cohen, 1989; McRae & Hetherington, 1993; Murre, 1992; RatcliŒ, 1990; Robins, 1995, 1996; Sharkey & Sharkey, 1995). Similar issues have been explored in the context of Hop® eld networks by Nadal et al. (1986) and Burgess et al. (1991). In a typical illustration of catastrophic forgetting,(1) we use a”
Catastrophic forgetting in connectionist networks. (1999, background): “97, 285–308 c Murre, J. (1992) Learning and Categorization in Modular Neural Networks,”
Sequential learning in neural networks: A review and a discussion of pseudorehearsal based methods (2004, unknown): “CALM, an explicitly modular network architecture [45], also stores new inputs using previously uncommitted nodes.”
Connectionist modelling in psychology: A localist manifesto (2000, background): “There has been a good deal of work on the subject since then (e.g., French 1991; 1994; Lewandowsky 1991; McRae & Hetherington 1993; Murre 1992; Sharkey & Sharkey 1995; Sloman & Rumelhart 1992), most of which has concluded that in order to reduce catastrophic interference one must reduce the overlap…”
Exemplar-Supported Generative Reproduction for Class Incremental Learning (2018, background): “Practical approaches include dual-memory models [2, 12], evolving networks [18, 31], weight consolidation [15], and other variants of neural networks [4, 23].”
Catastrophic Interference is Eliminated in Pretrained Networks (1993, background): “Standard networks tend to unlearn catastrophically because there are too few constraints on hidden unit representations when learning initial items (French, 1991; Hetherington, 1991; Kruschke, 1992; Murre, 1992).”