The Divergent Autoencoder (DIVA) Account of Human Category Learning
نویسنده
چکیده
The DIVA network model is introduced based on the novel computational principle of divergent autoencoding. DIVA produces excellent fits to classic data sets from Shepard, Hovland & Jenkins (1961) and Medin & Schafffer (1978). DIVA is also resistant to catastrophic interference. Such results have not previously been demonstrated by a model that is not committed to both localist coding of exemplars (or exceptions) and the use of an explicit selective attention mechanism.
منابع مشابه
Evaluating the Divergent Auto-Encoder (DIVA) as a Machine Learning Algorithm
The divergent auto-encoder (Kurtz, 2007) offers an alternative to the multi-layer perceptron (MLP) for classification learning via back-propagation. The artificial neural network classifies based on its success reconstructing the input features (from shared, reduced dimensionality recodings) in terms of a generative model of each category. Successful simulations of rapid human learning of eleme...
متن کاملModels of Human Category Learning: Do they Generalize?
Generalization to new examples is an essential aspect of categorization. However, recent category learning research has not focused on how people generalize their category knowledge. Taking generalization to be a critical basis for evaluating formal models of category learning, we employed a ‘minimal case’ approach to begin a systematic investigation of generalization. Human participants receiv...
متن کاملA Connectionist Account of Perceptual Category-Learning in Infants
This paper presents a connectionist model of correlationbased categorization by 10-month-old infants (Younger, 1985). Simple autoencoder networks were exposed to the same stimuli used to test 10-month-olds. Both infants and networks used co-variation information (when available) to segregate items into separate categories. The model provides a mechanistic account of category learning within a t...
متن کاملExemplar models can't see the forest for the trees
We investigated human learning and generalization of three novel category structures based on eight exemplars in a continuous (9x9) stimulus space. Each category requires attention to both dimensions, but they differ in their organization. Critically, all three category types are matched on withinand between-category exemplar distances. The first category structure conforms to a condensation or...
متن کاملAsymmetric interference in 3- to 4-month-olds' sequential category learning
Threeto 4-month-old infants show asymmetric exclusivity in the acquisition of cat and dog perceptual categories. The cat perceptual category excludes dog exemplars, but the dog perceptual category does not exclude cat exemplars. We describe a connectionist autoencoder model of perceptual categorization that shows the same asymmetries as infants. The model predicts the presence of asymmetric ret...
متن کامل