Category dimensionality and feature knowledge: when more features are learned as easily as fewer

Ensemble stacking rockburst prediction model based on Yeo-Johnson, K-means SMOTE, and optimal rockburst feature dimension determination

Rockburst forecasting plays a crucial role in prevention and control of rockburst disaster. To improve the accuracy of rockburst prediction at the data structure and algorithm levels, the Yeo–Johnson transform, K-means SMOTE oversampling, and optimal rockburst feature dimension determination are used to optimize the data structure. At the algorithm optimization level, ensemble stacking rockburst prediction is performed based on the data structure optimization. First, to solve the problem of many outliers and data imbalance in the distribution of rockburst data, the Yeo–Johnson transform and k-means SMOTE algorithm are respectively used to solve the problems. Then, based on six original rockburst features, 21 new features are generated using the PolynomialFeatures function in Sklearn. Principal component analysis (PCA) dimensionality reduction is applied to eliminate the correlations between the 27 features. Thirteen types of machine learning algorithms are used to predict datasets that retain different numbers of features after dimensionality reduction to determine the optimal rockburst feature dimension. Finally, the 14-feature rockburst dataset is used as the input for integrated stacking. The results show that the ensemble stacking model based on Yeo–Johnson, K-means SMOTE, and optimal rockburst feature dimension determination can improve the accuracy of rockburst prediction by 0.1602–0.3636. Compared with the 13 single machine learning models without data preprocessing, this data structure optimization and algorithm optimization method effectively improves the accuracy of rockburst prediction.

Mitigating cue competition effects in human category learning

When people learn perceptual categories, if one feature makes it easy to determine the category membership, learning about other features can be reduced. In three experiments, we asked whether this cue competition effect could be fully eradicated with simple instructions. For this purpose, in a pilot experiment, we adapted a classical overshadowing paradigm into a human category learning task. Unlike previous reports, we demonstrate a robust cue competition effect with human learners. In Experiments 1 and 2, we created a new warning condition that aimed at eradicating the cue competition effect through top-down instructions. With a medium-size overshadowing effect, Experiment 1 shows a weak mitigation of the overshadowing effect. We replaced the stimuli in Experiment 2 to obtain a larger overshadowing effect and showed a larger warning effect. Nevertheless, the overshadowing effect could not be fully eradicated. These experiments suggest that cue competition effects can be a stubborn roadblock in human category learning. Theoretical and practical implications are discussed.

Do Additional Features Help or Hurt Category Learning? The Curse of Dimensionality in Human Learners

The curse of dimensionality, which has been widely studied in statistics and machine learning, occurs when additional features cause the size of the feature space to grow so quickly that learning classification rules becomes increasingly difficult. How do people overcome the curse of dimensionality when acquiring real-world categories that have many different features? Here we investigate the possibility that the structure of categories can help. We show that when categories follow a family resemblance structure, people are unaffected by the presence of additional features in learning. However, when categories are based on a single feature, they fall prey to the curse, and having additional irrelevant features hurts performance. We compare and contrast these results to three different computational models to show that a model with limited computational capacity best captures human performance across almost all of the conditions in both experiments.

Do salient features overshadow learning of other features in category learning?

Hundreds of associative learning experiments have examined how animals learn to predict an aversive outcome, such as a shock, loud sound, or puff of air in the eye. In this study, we reversed this pattern and examined the role of an aversive stimulus, shock, as a feature of a complex stimulus composed of several features, rather than as an outcome. In particular, we used a category learning paradigm in which multiple features predicted category membership and asked whether a salient, aversive feature would reduce learning of other category features through cue competition. Three experiments compared a condition in which 1 category had among its 6 features a painful "sting" (shock) and the other category a distinctive sound (the critical features) to a control condition in which the sting and sound were represented by much less salient (and not aversive) visual depictions. Subjects learned the categories and then were tested on their knowledge of all 6 features as predictors of the category label. Surprisingly, the experiments consistently found that the salient, aversive critical features did not reduce learning of other features relative to the control. Bayesian statistics gave positive evidence for this null result. Equally surprisingly, in a fourth experiment, a nonaversive salient feature (brightly colored patterns) increased learning of other features compared to the control. We explain the results in terms of attentional strategies that may apply in a category learning context. (PsycINFO Database Record

Observation versus classification in supervised category learning

The traditional supervised classification paradigm encourages learners to acquire only the knowledge needed to predict category membership (a discriminative approach). An alternative that aligns with important aspects of real-world concept formation is learning with a broader focus to acquire knowledge of the internal structure of each category (a generative approach). Our work addresses the impact of a particular component of the traditional classification task: the guess-and-correct cycle. We compare classification learning to a supervised observational learning task in which learners are shown labeled examples but make no classification response. The goals of this work sit at two levels: (1) testing for differences in the nature of the category representations that arise from two basic learning modes; and (2) evaluating the generative/discriminative continuum as a theoretical tool for understand learning modes and their outcomes. Specifically, we view the guess-and-correct cycle as consistent with a more discriminative approach and therefore expected it to lead to narrower category knowledge. Across two experiments, the observational mode led to greater sensitivity to distributional properties of features and correlations between features. We conclude that a relatively subtle procedural difference in supervised category learning substantially impacts what learners come to know about the categories. The results demonstrate the value of the generative/discriminative continuum as a tool for advancing the psychology of category learning and also provide a valuable constraint for formal models and associated theories.

Learning from observation, feedback, and intervention in linear and non-linear task environments

This multiple-cue judgment study investigates whether we can manipulate the judgment strategy and increase accuracy in linear and non-linear cue-criterion environments just by changing the training mode. Three experiments show that accuracy in simple linear additive task environments are improved with feedback training and intervention training, while accuracy in complex multiplicative tasks are improved with observational training. The observed interaction effect suggests that the training mode invites different strategies that are adjusted as a function of experience to the demands from the underlying cue-criterion structure. Thus, feedback and the intervention training modes invite cue abstraction, an effortful but successful strategy in combination with simple linear task structures, and observational training invites exemplar memory processes, a simple but successful strategy in combination with complex non-linear task structures. The study discusses adaptive cognition and the implication of the different training modes across a life span and for clinical populations.

Categorization = decision making + generalization

We rarely, if ever, repeatedly encounter exactly the same situation. This makes generalization crucial for real world decision making. We argue that categorization, the study of generalizable representations, is a type of decision making, and that categorization learning research would benefit from approaches developed to study the neuroscience of decision making. Similarly, methods developed to examine generalization and learning within the field of categorization may enhance decision making research. We first discuss perceptual information processing and integration, with an emphasis on accumulator models. We then examine learning the value of different decision making choices via experience, emphasizing reinforcement learning modeling approaches. Next we discuss how value is combined with other factors in decision making, emphasizing the effects of uncertainty. Finally, we describe how a final decision is selected via thresholding processes implemented by the basal ganglia and related regions. We also consider how memory related functions in the hippocampus may be integrated with decision making mechanisms and contribute to categorization.

Extending the Implicit Association Test (IAT): assessing consumer attitudes based on multi-dimensional implicit associations

Background

The authors present a procedural extension of the popular Implicit Association Test (IAT; [1]) that allows for indirect measurement of attitudes on multiple dimensions (e.g., safe–unsafe; young–old; innovative–conventional, etc.) rather than on a single evaluative dimension only (e.g., good–bad).

Methodology/Principal Findings

In two within-subjects studies, attitudes toward three automobile brands were measured on six attribute dimensions. Emphasis was placed on evaluating the methodological appropriateness of the new procedure, providing strong evidence for its reliability, validity, and sensitivity.

Conclusions/Significance

This new procedure yields detailed information on the multifaceted nature of brand associations that can add up to a more abstract overall attitude. Just as the IAT, its multi-dimensional extension/application (dubbed md-IAT) is suited for reliably measuring attitudes consumers may not be consciously aware of, able to express, or willing to share with the researcher [2], [3].

Prior knowledge enhances the category dimensionality effect

A study of the combined influence of prior knowledge and stimulus dimensionality on category learning was conducted. Subjects learned category structures with the same number of necessary dimensions but with more or fewer additional, redundant dimensions and with either knowledge-related or knowledge-unrelated features. Minimal-learning models predict that all subjects, regardless of condition, either should learn the same number of dimensions or should respond more slowly to each dimension. Despite similar learning rates and response times, subjects learned more features in the high-dimensional than in the low-dimensional condition. Furthermore, prior knowledge interacted with dimensionality, increasing what was learned, especially in the high-dimensional case. A second experiment confirmed that the participants did, in fact, learn more features during the training phase, rather than simply inferring them at test. These effects can be explained by direct associations among features (representing prior knowledge), combined with feedback between features and the category label, as was shown by simulations of the knowledge resonance, or KRES, model of category learning.

Blocking in category learning

Many theories of category learning assume that learning is driven by a need to minimize classification error. When there is no classification error, therefore, learning of individual features should be negligible. The authors tested this hypothesis by conducting three category-learning experiments adapted from an associative learning blocking paradigm. Contrary to an error-driven account of learning, participants learned a wide range of information when they learned about categories, and blocking effects were difficult to obtain. Conversely, when participants learned to predict an outcome in a task with the same formal structure and materials, blocking effects were robust and followed the predictions of error-driven learning. The authors discuss their findings in relation to models of category learning and the usefulness of category knowledge in the environment.