D
Daniel Huang
Researcher at University of California, Berkeley
Publications - 18
Citations - 308
Daniel Huang is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Probabilistic logic. The author has an hindex of 8, co-authored 13 publications receiving 268 citations. Previous affiliations of Daniel Huang include Business International Corporation & Harvard University.
Papers
More filters
Proceedings ArticleDOI
Segmentation fusion for connectomics
Amelio Vazquez-Reina,Michael A. Gelbart,Daniel Huang,Jeff W. Lichtman,Eric L. Miller,Hanspeter Pfister +5 more
TL;DR: This work identifies the fusion of segments and links that provide the most globally consistent segmentation of the stack and shows that this two-step approach of pre-enumeration and posterior fusion yields significant advantages and provides state-of-the-art reconstruction results.
Proceedings Article
GamePad: A Learning Environment for Theorem Proving
TL;DR: A system called GamePad is introduced that can be used to explore the application of machine learning methods to theorem proving in the Coq proof assistant and addresses position evaluation and tactic prediction tasks, which arise naturally in tactic-based theorem proving.
Posted Content
GamePad: A Learning Environment for Theorem Proving
TL;DR: In this paper, the authors introduce a system called GamePad that can be used to explore the application of machine learning methods to theorem proving in the Coq proof assistant in a step-by-step manner.
Proceedings ArticleDOI
Compiling Markov chain Monte Carlo algorithms for probabilistic modeling
TL;DR: A compiler is described that transforms a probabilistic model written in a restricted modeling language and a query for posterior samples given observed data into a Markov Chain Monte Carlo (MCMC) inference algorithm that implements the query.
Proceedings Article
Augur: Data-Parallel Probabilistic Modeling
Jean-Baptiste Tristan,Daniel Huang,Joseph Tassarotti,Adam Craig Pocock,Stephen J. Green,Guy L. Steele +5 more
TL;DR: Augur is presented, a probabilistic modeling language and compiler for Bayesian networks designed to make effective use of data-parallel architectures such as GPUs and it is shown that the compiler can generate data-Parallel inference code scalable to thousands of GPU cores by making use of the conditional independence relationships in the Bayesian network.