Gyslain Giguère

FEBAM: A Feature-Extracting Bidirectional Associative Memory

In this paper, a new model that can ultimately create its own set of perceptual features is proposed. Using a bidirectional associative memory (BAM)-inspired architecture, the resulting model inherits properties such as attractor-like behavior and successful processing of noisy inputs, while being able to achieve principal component analysis (PCA) tasks such as feature extraction and dimensionality reduction. The model is tested by simulating image reconstruction and blind source separation tasks. Simulations show that the model fares particularly well compared to current neural PCA and independent component analysis (ICA) algorithms. It is argued the model possesses more cognitive explanative power than any other nonlinear/linear PCA and ICA algorithm.

The Origin of Exemplar Effects in Rule-Driven Categorization

S. W. Allen and L. R. Brooks (1991) have shown that exemplar memory can affect categorization even when participants are provided with a classification rule. G. Regehr and L. R. Brooks (1993) argued that stimuli must be individuated for such effects to occur. In this study, the authors further analyze the conditions that yield exemplar effects in this rule application paradigm. The results of Experiments 1-3 show that interchangeable attributes, which are not part of the rule, influence categorization only when attention is explicitly drawn on them. Experiment 4 shows that exemplar effects can occur in an incidental learning condition, whether stimulus individuation is preserved or not. The authors conclude that the influence of exemplar learning in rule-driven categorization stems from the attributes specified in the rule or in the instructions, not from the stimulus gestalts.

Learning the correlational structure of stimuli in a one-attribute classification task

In category learning experiments, participants typically do not learn within-category correlations unless the composition of the categories or the task demands compel them to do so. To determine if correlations among attributes could be learned without explicitly focusing the participants’ attention on them, a task was designed that allowed stimuli to be classified on the basis of a single perfectly predictive attribute. Each training stimulus also included attributes that were either perfectly or partly correlated with the rule attribute. Then, in a test phase, the impact of eliminating the rule attribute on classification was evaluated. The experiment showed that some of the attributes that were perfectly correlated with the rule attribute were learned. These attributes could be used to classify the test exemplars even though the rule attribute had been removed. This experiment provides evidence that within-category correlations can be learned incidentally during classification tasks.

Bidirectional Associative Memories, Self-Organizing Maps and k-Winners-Take-All: Uniting feature extraction and topological principles

In this paper, we introduce a network combining k-Winners-Take-All and Self-Organizing Map principles within a Feature Extracting Bidirectional Associative Memory. When compared with its “strictly winner-take-all” version, the modified model shows increased performance for clustering, by producing a better weight distribution and a lower dispersion level (higher density) for each given category. Moreover, because the model is recurrent, it is able to develop prototype representations strictly from exemplar encounters. Finally, just like any recurrent associative memory, the model keeps its reconstructive memory and noise filtering properties.

Using knowledge partitioning to investigate the psychological plausibility of mixtures of experts

Over the years, the presence of knowledge partitioning (KP) in human function learning data has been used to argue that mixture-of-experts models (MOE) constitute a psychologically plausible explanation of human performance, and that the experts used by humans are always linear. These claims recently led to the proposition of the population of linear experts model (POLE). In this paper, variations of the firefighting paradigm developed by Lewandowsky and his colleagues, which initiated research about KP, were used to explore the psychological plausibility of MOE in general and POLE in particular. In a first experiment, these statements were tested by modifying the test display of the firefighting paradigm. The results showed that adding irrelevant information to the display resulted in a smaller proportion of partitioning participants. Also, some participants used non-linear experts to partition the stimulus space. This new type of KP was further explored in a second study, which included more training sessions. The results suggest that linear KP disappears with practice and that non-linear partitioning reflects the incapacity to correctly estimate the position of the function’s vertex. It is concluded that MOE are adequate psychological models, but that the linearity and ubiquity claims of the POLE model need to be weakened.