One of the advantages of supervised learning is that the final error met(cid:173) ric is available during training. For classifiers, the algorithm can directly reduce the number of misclassifications on the training set. Unfortu(cid:173) nately, when modeling human learning or constructing classifiers for au(cid:173) tonomous robots, supervisory labels are often not available or too ex(cid:173) pensive. In this paper we show that we can substitute for the labels by making use of structure between the pattern distributions to different sen(cid:173) sory modalities. We show that minimizing the disagreement between the outputs of networks processing patterns from these different modalities is a sensible approximation to minimizing the number of misclassifications in each modality, and leads to similar results.

The key is to process the "moo" sound to obtain a self-supervised label for the network processing the visual image of the cow and vice-versa.

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn similarly. They often rely on data rigorously preprocessed to learn solutions to specific problems such as classification or regression. In particular, they forget their past learning experiences if trained on new ones. Therefore, artificial neural networks are often inept to deal with real-life settings such as an autonomous-robot that has to learn on-line to adapt to new situations and overcome new problems without forgetting its past learning-experiences. Continual learning (CL) is a branch of machine learning addressing this type of problem. Continual algorithms are designed to accumulate and improve knowledge in a curriculum of learning-experiences without forgetting. In this thesis, we propose to explore continual algorithms with replay processes. Replay processes gather together rehearsal methods and generative replay methods. Generative Replay consists of regenerating past learning experiences with a generative model to remember them. Rehearsal consists of saving a core-set of samples from past learning experiences to rehearse them later. The replay processes make possible a compromise between optimizing the current learning objective and the past ones enabling learning without forgetting in sequences of tasks settings. We show that they are very promising methods for continual learning. Notably, they enable the re-evaluation of past data with new knowledge and the confrontation of data from different learning-experiences. We demonstrate their ability to learn continually through unsupervised learning, supervised learning and reinforcement learning tasks.

We represent objects with n-dimensional pattern vectors and consider piecewise-linear classifiers consisting of a collection of (labeled) codebook vectors in the space of the input patterns (See Figure 1). The classification boundaries are gi ven by the voronoi tessellation of the codebook vectors. Patterns are said to belong to the class (given by the label) of the codebook vector to which they are closest.

We represent objects with n-dimensional pattern vectors and consider piecewise-linear classifiers consisting of a collection of (labeled) codebook vectors in the space of the input patterns (See Figure 1). The classification boundaries are gi ven by the voronoi tessellation of the codebook vectors. Patterns are said to belong to the class (given by the label) of the codebook vector to which they are closest.

Department of Computer Science University of Rochester Rochester, NY 14627 Abstract One of the advantages of supervised learning is that the final error metric isavailable during training. For classifiers, the algorithm can directly reduce the number of misclassifications on the training set. Unfortunately, whenmodeling human learning or constructing classifiers for autonomous robots,supervisory labels are often not available or too expensive. In this paper we show that we can substitute for the labels by making use of structure between the pattern distributions to different sensory modalities.We show that minimizing the disagreement between the outputs of networks processing patterns from these different modalities is a sensible approximation to minimizing the number of misclassifications in each modality, and leads to similar results. Using the Peterson-Barney vowel dataset we show that the algorithm performs well in finding appropriate placementfor the codebook vectors particularly when the confuseable classes are different for the two modalities. 1 INTRODUCTION This paper addresses the question of how a human or autonomous robot can learn to classify new objects without experience with previous labeled examples.