Deep learning has become a ubiquitous technology to improve machine intelligence.

We present an effective method for supervised feature construction.

In this paper, we study the pooled data problem of identifying the labels associated with a large collection of items, based on a sequence of pooled tests revealing the counts of each label within the pool. In the noiseless setting, we identify an exact asymptotic threshold on the required number of tests with optimal decoding, and prove a phase transition between complete success and complete failure. In addition, we present a novel noisy variation of the problem, and provide an information-theoretic framework for characterizing the required number of tests for general random noise models. Our results reveal that noise can make the problem considerably more difficult, with strict increases in the scaling laws even at low noise levels. Finally, we demonstrate similar behavior in an approximate recovery setting, where a given number of errors is allowed in the decoded labels.

It has been proven useful in several settings.

Neural Information Processing Systems http://nips.cc/

In this paper, we propose to exploit unlabeled videos for semi-supervised learning of optical flow with a Generative Adversarial Network.

This new formulation allows our algorithm to update basis functions online in accordance with the manifold structure of probability densities for fast convergence.

There is a large literature on this problem.

Often in machine learning, data are collected as a combination of multiple conditions, e.g., the voice recordings of multiple persons, each labeled with an ID.

Neural Information Processing Systems http://nips.cc/