On the other hand, discriminative methods such as support vector machines enable us to construct flexible decision boundaries and often result in classification performance superiorto that of the model based approaches. An ideal classifier should combine these two complementary approaches. In this paper, we develop a natural way of achieving this combination byderiving kernel functions for use in discriminative methods such as support vector machines from generative probability models.

On the other hand, discriminative methods such as support vector machines enable us to construct flexible decision boundaries and often result in classification performance superior to that of the model based approaches. An ideal classifier should combine these two complementary approaches. In this paper, we develop a natural way of achieving this combination by deriving kernel functions for use in discriminative methods such as support vector machines from generative probability models.

We study a particular type of Boltzmann machine with a bipartite graph structure called a harmonium. Ourinterest is in using such a machine to model a probability distribution on binary input vectors. We analyze the class of probability distributions that can be modeled by such machines.

In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.

We study a particular type of Boltzmann machine with a bipartite graph structure called a harmonium. Our interest is in using such a machine to model a probability distribution on binary input vectors. We analyze the class of probability distributions that can be modeled by such machines.

In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.

We address the question of when a network can be expected to generalize from m random training examples chosen from some arbitrary probabilitydistribution, assuming that future test examples are drawn from the same distribution. Among our results are the following bounds on appropriate sample vs. network size.

We address the question of when a network can be expected to generalize from m random training examples chosen from some arbitrary probability distribution, assuming that future test examples are drawn from the same distribution. Among our results are the following bounds on appropriate sample vs. network size.

See also: 2005 AAAI Classic Paper Awards summary of significance by Tom Mitchell in AI Magazine 26(4), 2005.Proc. AAAI-86