We consider the problem of how the CNS learns to control dynam(cid:173) ics of a mechanical system. By using a paradigm where a subject's hand interacts with a virtual mechanical environment, we show that learning control is via composition of a model of the imposed dynamics. Some properties of the computational elements with which the CNS composes this model are inferred through the gen(cid:173) eralization capabilities of the subject outside the training data.

When IBM's Deep Blue computer won its first game of chess against world champion Garry Kasparov in 1996, the public got a real taste of how powerful computers had become in competing with human intelligence. Since then, not only has computing power grown exponentially but the cost of processing power has fallen dramatically. These trends, combined with advances in artificial intelligence algorithms have enabled the development of systems that can, in some instances, perform tasks better than human beings. Video surveillance is one of these tasks; and certainly there is a large market opportunity given there has been little increase in the ability to analyze video, despite the massive growth in surveillance and in the storage of video data. According to IHS, 127 million surveillance cameras and 400 thousand body-worn cameras will ship in 2017 - in addition to the estimated 300 million cameras already deployed - and approximately 2.5 billion exabytes of data will be created every day.

We consider the problem of how the CNS learns to control dynamics of a mechanical system. By using a paradigm where a subject's hand interacts with a virtual mechanical environment, we show that learning control is via composition of a model of the imposed dynamics. Some properties of the computational elements with which the CNS composes this model are inferred through the generalization capabilities of the subject outside the training data.

We consider the problem of how the CNS learns to control dynamics of a mechanical system. By using a paradigm where a subject's hand interacts with a virtual mechanical environment, we show that learning control is via composition of a model of the imposed dynamics. Some properties of the computational elements with which the CNS composes this model are inferred through the generalization capabilities of the subject outside the training data.

We consider the problem of how the CNS learns to control dynamics ofa mechanical system. By using a paradigm where a subject's hand interacts with a virtual mechanical environment, we show that learning control is via composition of a model of the imposed dynamics. Some properties of the computational elements with which the CNS composes this model are inferred through the generalization capabilitiesof the subject outside the training data. 1 Introduction At about the age of three months, children become interested in tactile exploration of objects around them. They attempt to reach for an object, but often fail to properly control their arm and end up missing their target. In the ensuing weeks, they rapidly improve and soon they can not only reach accurately, they can also pick up the object and place it.