ALCOVE: an exemplar-based connectionist model of category learning.

By John K. Kruschke. 1992

How researchers see this paper

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

Citations in the corpus

Measuring Catastrophic Forgetting in Neural Networks (2017, positive): “ALCOVE is a shallow neural network that uses a sparse distance-based representation, which allows the weights assigned to older tasks to be largely unchanged when the network is presented with new data (Kruschke 1992).”
Online Continual Learning with Maximally Interfered Retrieval (2019, background): “While these problems have been studied in early research works [10, 11, 20, 21, 37], they are receiving increased attention since the revival of neural networks.”
Selfless Sequential Learning (2018, methodology): “This has led to several methods with the goal of orthogonalizing the activations (French, 1992; 1994; Kruschke, 1992; 1993; Sloman & Rumelhart, 1992).”
Word learning as Bayesian inference. (2007, methodology): “Similaritybased models of category learning that incorporate selective attention to different stimulus attributes (Kruschke, 1992) could in principle accomodate these results, but not without major modification.”
How bilinguals solve the naming problem (2005, background): “Many prominent models of categorization assume that similarity is the basis of categorization: Objects will tend to share names in proportion to their shared properties and in inverse proportion to the objects similarity to objects with different labels (Ashby & Maddox, 1992; Kruschke, 1992; Medin”
A catalog of Boolean concepts (2003, background): “The many subsequent studies of these types (e.g., Kruschke, 1992; Nosofsky, Gluck, Palmeri, McKinley, & Glauthier, 1994a; Nosofsky, Palmeri, & McKinley, 1994b) have consistently respected the typology up to congruence.”
Situated simulation in the human conceptual system (2003, background): “For specific applications of the feed-forward architecture to representing conceptual knowledge, see Hinton (1989), Kruschke (1992), and Rumelhart and Todd (1993).”
Using Semi-Distributed Representations to Overcome Catastrophic Forgetting in Connectionist Networks (1991, methodology): “Kortge, Chris A., [1990] , "ALCOVE: A exemplar-based connectionist model of category learning", , "Catastrophic interference in connectionist networks: , "Choice, similarity and the context theory of classification", , "Connections models of recognition memory: Constraints imposed by learning and fo”
Selective Attention and Transfer Phenomena in L2 Acquisition: Contingency, Cue Competition, Salience, Interference, Overshadowing, Blocking, and Perceptual Learning (2006, methodology): “Kruschke simulates these processes by building mechanisms of attention into his computational models of associative learning (ALCOVE (Kruschke 1992), ADIT (Kruschke 1996) and RASHNL (Kruschke and Johansen 1999)).”
Naming in young children: a dumb attentional mechanism? (1996, background): “Considerable evidence suggests that associative cues and the inherent pull of salient properties are universal aspects of attentional control and well documented in infants and children as well adults (Kruschke, 1992; Lewicki et al., 1989; Macintosh, 1965; Younger, 1990).”
Toward a unified model of attention in associative learning (2001, methodology): “This is the same 818 JOHN K. KRUSCHKE exemplar-similarity function used in the ALCOVE model (Kruschke, 1992) and in the generalized context model (Nosofsky, 1986).”
Generalization, similarity, and Bayesian inference. (2001, unknown): “A third class of models (Kruschke, 1992; Love & Medin, 1998) combines aspects of the first two, by embedding Shepard's exponential law within the activation functions of hidden units in a connectionist network for classification learning.”