skip to main content


Title: Predicting the Ease of Human Category Learning Using Radial Basis Function Networks
Abstract Our goal is to understand and optimize human concept learning by predicting the ease of learning of a particular exemplar or category. We propose a method for estimating ease values, quantitative measures of ease of learning, as an alternative to conducting costly empirical training studies. Our method combines a psychological embedding of domain exemplars with a pragmatic categorization model. The two components are integrated using a radial basis function network (RBFN) that predicts ease values. The free parameters of the RBFN are fit using human similarity judgments, circumventing the need to collect human training data to fit more complex models of human categorization. We conduct two category-training experiments to validate predictions of the RBFN. We demonstrate that an instance-based RBFN outperforms both a prototype-based RBFN and an empirical approach using the raw data. Although the human data were collected across diverse experimental conditions, the predicted ease values strongly correlate with human learning performance. Training can be sequenced by (predicted) ease, achieving what is known as fading in the psychology literature and curriculum learning in the machine-learning literature, both of which have been shown to facilitate learning.  more » « less
Award ID(s):
1631428
NSF-PAR ID:
10299594
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Neural Computation
Volume:
33
Issue:
2
ISSN:
0899-7667
Page Range / eLocation ID:
376 to 397
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    We apply the “wisdom of the crowd” idea to human category learning, using a simple approach that combines people's categorization decisions by taking the majority decision. We first show that the aggregated crowd category learning behavior found by this method performs well, learning categories more quickly than most or all individuals for 28 previously collected datasets. We then extend the approach so that it does not require people to categorize every stimulus. We do this using a model‐based method that predicts the categorization behavior people would produce for new stimuli, based on their behavior with observed stimuli, and uses the majority of these predicted decisions. We demonstrate and evaluate the model‐based approach in two case studies. In the first, we use the general recognition theory decision‐bound model of categorization (Ashby & Townsend,) to infer each person's decision boundary for two categories of perceptual stimuli, and we use these inferences to make aggregated predictions about new stimuli. In the second, we use the generalized context model exemplar model of categorization (Nosofsky,) to infer each person's selective attention for face stimuli, and we use these inferences to make aggregated predictions about withheld stimuli. In both case studies, we show that our method successfully predicts the category of unobserved stimuli, and we emphasize that the aggregated crowd decisions arise from psychologically interpretable processes and parameters. We conclude by discussing extensions and potential real‐world applications of the approach.

     
    more » « less
  2. Models of human categorization predict the prefrontal cortex (PFC) serves a central role in category learning. The dorsolateral prefrontal cortex (dlPFC) and ventromedial prefrontal cortex (vmPFC) have been implicated in categorization; however, it is unclear whether both are critical for categorization and whether they support unique functions. We administered three categorization tasks to patients with PFC lesions (mean age, 69.6 years; 5 men, 5 women) to examine how the prefrontal subregions contribute to categorization. These included a rule-based (RB) task that was solved via a unidimensional rule, an information integration (II) task that was solved by combining information from two stimulus dimensions, and a deterministic/probabilistic (DP) task with stimulus features that had varying amounts of category-predictive information. Compared with healthy comparison participants, both patient groups had impaired performance. Impairments in the dlPFC patients were largest during the RB task, whereas impairments in the vmPFC patients were largest during the DP task. A hierarchical model was fit to the participants’ data to assess learning deficits in the patient groups. PFC damage was correlated with a regularization term that limited updates to attention after each trial. Our results suggest that the PFC, as a whole, is important for learning to orient attention to relevant stimulus information. The dlPFC may be especially important for rule-based learning, whereas the vmPFC may be important for focusing attention on deterministic (highly diagnostic) features and ignoring less predictive features. These results support overarching functions of the dlPFC in executive functioning and the vmPFC in value-based decision-making.

     
    more » « less
  3. null (Ed.)
    Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting that aims to categorize documents effectively, with a couple of seed documents annotated per category. We recognize that texts collected from the Web are often structure-rich, i.e., accompanied by various metadata. One can easily organize the corpus into a text-rich network, joining raw text documents with document attributes, high-quality phrases, label surface names as nodes, and their associations as edges. Such a network provides a holistic view of the corpus’ heterogeneous data sources and enables a joint optimization for network-based analysis and deep textual model training. We therefore propose a novel framework for minimally supervised categorization by learning from the text-rich network. Specifically, we jointly train two modules with different inductive biases – a text analysis module for text understanding and a network learning module for class-discriminative, scalable network learning. Each module generates pseudo training labels from the unlabeled document set, and both modules mutually enhance each other by co-training using pooled pseudo labels. We test our model on two real-world datasets. On the challenging e-commerce product categorization dataset with 683 categories, our experiments show that given only three seed documents per category, our framework can achieve an accuracy of about 92%, significantly outperforming all compared methods; our accuracy is only less than 2% away from the supervised BERT model trained on about 50K labeled documents. 
    more » « less
  4. null (Ed.)
    Categorizing documents into a given label hierarchy is intuitively appealing due to the ubiquity of hierarchical topic structures in massive text corpora. Although related studies have achieved satisfying performance in fully supervised hierarchical document classification, they usually require massive human-annotated training data and only utilize text information. However, in many domains, (1) annotations are quite expensive where very few training samples can be acquired; (2) documents are accompanied by metadata information. Hence, this paper studies how to integrate the label hierarchy, metadata, and text signals for document categorization under weak supervision. We develop HiMeCat, an embedding-based generative framework for our task. Specifically, we propose a novel joint representation learning module that allows simultaneous modeling of category dependencies, metadata information and textual semantics, and we introduce a data augmentation module that hierarchically synthesizes training documents to complement the original, small-scale training set. Our experiments demonstrate a consistent improvement of HiMeCat over competitive baselines and validate the contribution of our representation learning and data augmentation modules. 
    more » « less
  5. Abstract

    Using the existing measures for training numerical (non-categorical) prediction models can cause misclassification of droughts. Thus, developing a drought category-based measure is critical. Moreover, the existing fixed drought category thresholds need to be improved. The objective of this research is to develop a category-based scoring support vector regression (CBS-SVR) model based on an improved drought categorization method to overcome misclassification in drought prediction. To derive variable threshold levels for drought categorization, K-means (KM) and Gaussian mixture (GM) clustering are compared with the traditional drought categorization. For drought prediction, CBS-SVR is performed by using the best categorization method. The new drought model was applied to the Red River of the North Basin (RRB) in the USA. In the model training and testing, precipitation, temperature, and actual evapotranspiration were selected as the predictors, and the target variables consisted of multivariate drought indices, as well as bivariate and univariate standardized drought indices. Results indicated that the drought categorization method, variable threshold levels, and the type of drought index were the major factors that influenced the accuracy of drought prediction. The CBS-SVR outperformed the support vector classification and traditional SVR by avoiding overfitting and miscategorization in drought prediction.

     
    more » « less