## Neural Computation

Even if it is not possible to reproduce a target input-output relation, a learning machine should be able to minimize the probability of making errors. A practical learning algorithm should also be simple enough to go without memorizing example data, if possible. Incremental algorithms such as error backpropagation satisfy this requirement. We propose incremental algorithms that provide fast convergence of the machine parameter θ to its optimal choice θ_{o} with respect to the number of examples *t*. We will consider the binary choice model whose target relation has a blurred boundary and the machine whose parameter θ specifies a decision boundary to make the output prediction. The question we wish to address here is how fast θ can approach θ_{o}, depending upon whether in the learning stage the machine can specify inputs as queries to the target relation, or the inputs are drawn from a certain distribution. If queries are permitted, the machine can achieve the fastest convergence, (θ - θ_{o})^{2} ∼ *O*(t^{−1}). If not, *O*(t^{−1}) convergence is generally not attainable. For learning without queries, we showed in a previous paper that the error minimum algorithm exhibits a slow convergence (θ - θ_{o})^{2} ∼ *O*(t^{−2/3}). We propose here a practical algorithm that provides a rather fast convergence, *O*(*t*^{−4/5}). It is possible to further accelerate the convergence by using more elaborate algorithms. The fastest convergence turned out to be *O*[(ln*t*)^{2}*t*^{−1}]. This scaling is considered optimal among possible algorithms, and is not due to the incremental nature of our algorithm.