Machine Learning, Machine Vision, and the Brain
Tomaso Poggio, Christian R. Shelton · 1999
The problem of learning is arguably at the very core of the problem of intelligence, both biological and artificial. In this paper we review our work over the last ten years in the area of supervised learning, focusing on three interlinked directions of research: theory, engineering applications (making intelligent software) and neuroscience (understanding the brain's mechanisms of learning) which contribute to and complement each other. Keywords: Machine Learning, Regularization, Support Vector Machine, IT Cortex, Function Approximation, Object Detection Learning Theory and Algorithms Engineering Applications, Plausibility Proofs Neuroscience: Models and Experiments Figure 1: A multidisciplinary approach to supervised learning 1 Introduction Learning is now perceived as a gateway to understanding the problem of intelligence. Since seeing is intelligence, learning is also becoming a key to the study of artificial and biological vision. In the last few years both com...