In this paper we propose an iterative learning control scheme based on the quasi-Newton method. The iterative learning control is designed to improve the performance of the systems working cyclically. We consider the general type of systems described by continuously diierentiable operator acting in Banach spaces. The suucient conditions for the convergence of quasi-Newton iterative learning alg...

| It is well-known that MultiLevel Coding (MLC) andMultiStage Decoding (MSD) su ce to approach capacity if the rates at di erent levels are chosen appropriately. In most of the practical cases, however, the rate design rule for MSD doesn't leave any room for coding at higher levels of the MLC scheme, which is very important in fading environments. In this paper, the rate design rule for multile...

Many biological pathways were first uncovered by identifying mutants with visible phenotypes and by scoring every sample in a screen via tedious and subjective visual inspection. Now, automated image analysis can effectively score many phenotypes. In practical application, customizing an image-analysis algorithm or finding a sufficient number of example cells to train a machine learning algorit...

Metric learning methods have been shown to perform well on different learning tasks. Many of them rely on target neighborhood relationships that are computed in the original feature space and remain fixed throughout learning. As a result, the learned metric reflects the original neighborhood relations. We propose a novel formulation of the metric learning problem in which, in addition to the me...

We give a polynomial-time algorithm for learning neural networks with one hidden layer of sigmoids feeding into any smooth, monotone activation function (e.g., sigmoid or ReLU). We make no assumptions on the structure of the network, and the algorithm succeeds with respect to any distribution on the unit ball in n dimensions (hidden weight vectors also have unit norm). This is the first assumpt...

In this paper, we propose an integrated policy learning framework that fuses iterative learning control (ILC) and reinforcement learning. Integration is accomplished at the exploration level of the reinforcement learning algorithm. The proposed algorithm combines fast convergence properties of iterative learning control and robustness of reinforcement learning. This way, the advantages of both ...