Bart Ons

Effects of category learning on the stimulus selectivity of macaque inferior temporal neurons

Primates can learn to categorize complex shapes, but as yet it is unclear how this categorization learning affects the representation of shape in visual cortex. Previous studies that have examined the effect of categorization learning on shape representation in the macaque inferior temporal (IT) cortex have produced diverse and conflicting results that are difficult to interpret owing to inadequacies in design. The present study overcomes these issues by recording IT responses before and after categorization learning. We used parameterized shapes that varied along two shape dimensions. Monkeys were extensively trained to categorize the shapes along one of the two dimensions. Unlike previous studies, our paradigm counterbalanced the relevant categorization dimension across animals. We found that categorization learning increased selectivity specifically for the category-relevant stimulus dimension (i.e., an expanded representation of the trained dimension), and that the ratio of within-category response similarities to between-category response similarities increased for the relevant dimension (i.e., category tuning). These small effects were only evident when the learned category-related effects were disentangled from the prelearned stimulus selectivity. These results suggest that shape-categorization learning can induce minor category-related changes in the shape tuning of IT neurons in adults, suggesting that learned, category-related changes in neuronal response mainly occur downstream from IT.

Development of Differential Sensitivity for Shape Changes Resulting from Linear and Nonlinear Planar Transformations

A shape bias for extending names to objects that look visually similar has been commonly accepted but it is hard to define which kind of shape dissimilarities are diagnostic for the identity of an object. Here, we present a transformational approach to describe shape differences that can incorporate many significant shape features. We introduce two kinds of transformations: one kind concerns linear transformations of the image plane (affine transformations), generally limiting shape variations within the borders of basic-level categories; the other kind concerns nonlinear continuous transformations of the image plane (topological transformations), allowing all kinds of shape variation crossing and not crossing the borders of basic-level categories. We administered stimulus pairs differing in these shape transformations to children of 3 years to 7 years old in a delayed match-to-sample task. With increasing age, especially between 5 years and 6 years, children became more sensitive to the topological deformations that are relevant for between-category distinctions, indicating that acquired categorical knowledge in early years induces perceptual learning of the relevant generic shape differences between categories.

Acquisition of ordinal words using weakly supervised NMF

This paper issues in the design of a vocal interface for a robot that can learn to understand spoken utterances through demonstration. Weakly supervised non-negative matrix factorization (NMF) is used as a machine learning algorithm where acoustic data are augmented with semantic labels representing the meaning of the command. Many parameters that the robot needs in order to execute the commands have an ordinal structure. Constrained subspace NMF (CSNMF) is proposed as an extension to NMF that aims to better deal with ordinal data and thus increase the learning rate of the grounding information with an ordinal structure. Furthermore automatic relevance determination is used to deal with model order selection. The use of CSNMF yields a significant improvement in the learning rate and accuracy when recognising ordinal parameters.

Label Noise Robustness and Learning Speed in a Self-Learning Vocal User Interface

A self-learning vocal user interface learns to map user-defined spoken commands to intended actions. The voice user interface is trained by mining the speech input and the provoked action on a device. Although this generic procedure allows a great deal of flexibility, it comes at a cost. Two requirements are important to create a user-friendly learning environment. First, the self-learning interface should be robust against typical errors that occur in the interaction between a non-expert user and the system. For instance, the user gives a wrong learning example to the system by commanding “Turn on the television!” and pushing a power button on the wrong remote control. The spoken command is then supervised by a wrong action and we refer to these errors as label noise. Secondly, the mapping between voice commands and intended actions should happen fast, i.e. require few examples. To meet these requirements, we implemented learning through supervised NMF. We tested keyword recognition accuracy for different levels of label noise and different sizes of training sets. Our learning approach is robust against label noise, but some improvement regarding fast mapping is desirable.

Fast vocabulary acquisition in an NMF-based self-learning vocal user interface

Abstract In command-and-control applications, a vocal user interface (VUI) is useful for handsfree control of various devices, especially for people with a physical disability. The spoken utterances are usually restricted to a predefined list of phrases or to a restricted grammar, and the acoustic models work well for normal speech. While some state-of-the-art methods allow for user adaptation of the predefined acoustic models and lexicons, we pursue a fully adaptive VUI by learning both vocabulary and acoustics directly from interaction examples. A learning curve usually has a steep rise in the beginning and an asymptotic ceiling at the end. To limit tutoring time and to guarantee good performance in the long run, the word learning rate of the VUI should be fast and the learning curve should level off at a high accuracy. In order to deal with these performance indicators, we propose a multi-level VUI architecture and we investigate the effectiveness of alternative processing schemes. In the low-level layer, we explore the use of MIDA features (Mutual Information Discrimination Analysis) against conventional MFCC features. In the mid-level layer, we enhance the acoustic representation by means of phone posteriorgrams and clustering procedures. In the high-level layer, we use the NMF (Non-negative Matrix Factorization) procedure which has been demonstrated to be an effective approach for word learning. We evaluate and discuss the performance and the feasibility of our approach in a realistic experimental setting of the VUI-user learning context.

NMF-based keyword learning from scarce data

This research is situated in a project aimed at the development of a vocal user interface (VUI) that learns to understand its users specifically persons with a speech impairment. The vocal interface adapts to the speech of the user by learning the vocabulary from interaction examples. Word learning is implemented through weakly supervised non-negative matrix factorization (NMF). The goal of this study is to investigate how we can improve word learning when the number of interaction examples is low. We demonstrate two approaches to train NMF models on scarce data: 1) training word models using smoothed training data, and 2) training word models that strictly correspond to the grounding information derived from a few interaction examples. We found that both approaches can substantially improve word learning from scarce training data.

A computational model of visual anisotropy.

Visual anisotropy has been demonstrated in multiple tasks where performance differs between vertical, horizontal, and oblique orientations of the stimuli. We explain some principles of visual anisotropy by anisotropic smoothing, which is based on a variation on Koenderinks approach in [1]. We tested the theory by presenting Gaussian elongated luminance profiles and measuring the perceived orientations by means of an adjustment task. Our framework is based on the smoothing of the image with elliptical Gaussian kernels and it correctly predicted an illusory orientation bias towards the vertical axis. We discuss the scope of the theory in the context of other anisotropies in perception.

A developmental difference in shape processing and word-shape associations between 4 and 6.5 year olds

In distinguishing individual shapes (defined by their contours), older children (6.5 years of age on average) performed better than younger children (4 years of age on average), and, although the task did not involve any categorization or generalization, the error pattern was qualitatively affected by shape differences that are generally common distinctions between objects belonging to different categories. The influence of these shape differences was also observed for unfamiliar shapes, demonstrating that the influence of categorization experience was not modulated by the retrieval of shape features from known categories but rather related to a different perception of shape by age. The results suggest a direct influence of categorization experience on more abstract shape processing. When children were distinguishing shapes, new words were paired with the target shapes, and in 2 additional tasks, the acquired name–shape associations were tested. The younger age group was able to remember more words correctly.