Human Category Learning: Implications for Backpropagation Models

By John K. Kruschke. 1993

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

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.”
Continual learning: A comparative study on how to defy forgetting in classification tasks (2019, background): “Several directions have been explored, such as reducing representation overlap [22], [34], [35], [36], [37], replaying samples or virtual samples from the past [10], [24] or introducing dual architectures [38], [39], [40].”
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).”
Selective Attention and Transfer Phenomena in L2 Acquisition: Contingency, Cue Competition, Salience, Interference, Overshadowing, Blocking, and Perceptual Learning (2006, background): “Research shows this to routinely occur even in very simple learning situations like these (Kruschke 1993, 1996, 2001; Kruschke and Blair 2000; Kruschke and Johansen 1999; Shanks 1995) —they are not restricted to complex learning environments with dozens of cues and outcomes and intricate…”
Online Task-free Continual Learning with Dynamic Sparse Distributed Memory (2022, methodology): “This was done in several ways, either by gradually nudging the network’s internal representations into largely non-overlapping clusters [49] or by orthogonalizing the input representations [15, 33, 35].”
The neuropsychology of impulsive antisocial sensation seeking personality traits: From dopamine to hippocampal function (2004, methodology): “with Ball & Zuckerman (1990), the CL task used was of the rapidly learned, rule-based type that was based on Kruschke (1993) .”
Self-refreshing memory in artificial neural networks: learning temporal sequences without catastrophic forgetting (2004, background): “Hintzman 1986, Grossberg 1987, Kanerva 1988, Kruschke 1992, 1993, Ans et al. 1998), good generalization often requires a highly distributed system; and along with this high degree of distribution comes catastrophic interference.”
SUSTAIN: a network model of category learning. (2004, background): “Humans also find unidimensional problems easier to master than other linear problems that require attending to multiple dimensions (Ashby, Alfonso-Reese, Turken, & Waldron, 1998; Ashby, Queller, & Berretty, 1999; Kruschke, 1993; McKinley & Nosofsky, 1996).”
Bayesian Cognitive Modeling: A Practical Course (2014, methodology): “• Kruschke, J. K. (2010). Doing Bayesian Data Analysis: A Tutorial Introduction with R and BUGS. Burlington, MA: Academic Press. This is one of the first Bayesian books geared explicitly towards experimental psychologists and cognitive scientists. Kruschke explains core Bayesian concepts with concre”
Neural networks with a self-refreshing memory: Knowledge transfer in sequential learning tasks without catastrophic forgetting (2000, background): “Other memory models that use separate or sparse distributed representations face this dilemma to a lesser extent (e.g. Hintzman 1986, Grossberg 1987, Kanerva 1988, Krushke 1992, 1993, Ans et al. 1998).”
Continual Learning in Neural Networks (2019, methodology): “This led to several methods with the goal of orthogonalizing the activations [39, 40, 78, 79, 144].”
Toward a unified model of attention in associative learning (2001, background): “The right-hand side of Fig. 5 shows data from people who learned the structures, where it can be seen that filtration is much easier than condensation ( Kruschke, 1993 ).”
Journal of Experimental Psychology: Human Perception and Performance (2006, unknown): “Work in multidimensional categorization suggests that, in the case of highly separable dimensions, observers selectively attend to component dimensions both in learning and in generalizing to novel transfer stimuli (Kruschke, 1993; Nosofsky, 1989; Shepard, Hovland, & Jenkins, 1961).”
From covariation to causation: A causal power theory. (1997, methodology): “…in Pavlovian conditioning and causal induction, another reason I am focusing on the model is that the learning rule it incorporates is a version of the "delta rule" commonly used in connectionist models (e.g., Kruschke, 1992, 1993; McClelland & Rumelhart, 1985; Rumelhart & McClelland, 1986).”