J
John Platt
Researcher at Microsoft
Publications - 369
Citations - 66980
John Platt is an academic researcher from Microsoft. The author has contributed to research in topics: Support vector machine & Artificial neural network. The author has an hindex of 83, co-authored 369 publications receiving 60242 citations. Previous affiliations of John Platt include Google & California Institute of Technology.
Papers
More filters
PatentDOI
Method and apparatus for denoising and deverberation using variational inference and strong speech models
TL;DR: In this article, the probability distributions of the speech model parameters and the denoised values are adjusted to improve a variational inference so that the variational inferential inference better approximates the joint probability of the speaker's parameters and denoising values given a noisy signal.
Learning annotated hierarchies from relational data
TL;DR: A generative model for annotated hierarchy and the features and relations that they describe are defined, and a Markov chain Monte Carlo scheme for learning annotated hierarchies is developed.
Active learning for misspecified generalized linear models
TL;DR: In this paper, an asymptotic analysis of active learning for generalized linear models is presented under the common practical situation of model misspecification, and is based on realistic assumptions regarding the nature of the sampling distributions, which are usually neither independent nor identical.
Patent
Game-powered search engine
TL;DR: In this article, the authors present a system and method that facilitates an interactive game-powered search engine that serve the purposes of both users who may be looking for information as well as game participants who may desire to earn some reward or level of enjoyment by playing the game.
Blind Motion Deblurring Using Image Statistics
TL;DR: This work addresses the problem of blind motion deblurring from a single image, caused by a few moving objects, and relies on the observation that the statistics of derivative filters in images are significantly changed by blur.