#### Filter Results:

- Full text PDF available (29)

#### Publication Year

2006

2018

- This year (1)
- Last 5 years (28)
- Last 10 years (48)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard S. Zemel
- ArXiv
- 2016

This work on GGS-NN is motivated by the program verification application, where we need to analyze dynamic data structures created in the heap. On a very high level, in this application a machineâ€¦ (More)

We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to predict properties ofâ€¦ (More)

- Daniel Tarlow, Inmar E. Givoni, Richard S. Zemel
- AISTATS
- 2010

There is a growing interest in building probabilistic models with high order potentials (HOPs), or interactions, among discrete variables. Message passing inference in such models generally takesâ€¦ (More)

- Miltiadis Allamanis, Daniel Tarlow, Andrew D. Gordon, Yi Wei
- ICML
- 2015

We consider the problem of building probabilistic models that jointly model short natural language utterances and source code snippets. The aim is to bring together recent work on statisticalâ€¦ (More)

- Alexander L. Gaunt, Marc Brockschmidt, +4 authors Daniel Tarlow
- ArXiv
- 2016

We study machine learning formulations of inductive program synthesis; that is, given input-output examples, synthesize source code that maps inputs to corresponding outputs. Our key contribution isâ€¦ (More)

- David A. Ross, Daniel Tarlow, Richard S. Zemel
- International Journal of Computer Vision
- 2010

Humans demonstrate a remarkable ability to parse complicated motion sequences into their constituent structures and motions. We investigate this problem, attempting to learn the structure of one orâ€¦ (More)

- Daniel Tarlow, Ryan P. Adams, Richard S. Zemel
- AISTATS
- 2012

One approach to modeling structured discrete data is to describe the probability of states via an energy function and Gibbs distribution. A recurring difficulty in these models is the computation ofâ€¦ (More)

- Chris J. Maddison, Daniel Tarlow
- ICML
- 2014

We study the problem of building generative models of natural source code (NSC); that is, source code written and understood by humans. Our primary contribution is to describe a family of generativeâ€¦ (More)

- John C. Duchi, Daniel Tarlow, Gal Elidan, Daphne Koller
- NIPS
- 2006

In general, the problem of computing a maximum a posteriori (MAP) assignment in a Markov random field (MRF) is computationally intractable. However, in certain subclasses of MRF, an optimal orâ€¦ (More)

- Yujia Li, Daniel Tarlow, Richard S. Zemel
- IEEE Conference on Computer Vision and Patternâ€¦
- 2013

When modeling structured outputs such as image segmentations, prediction can be improved by accurately modeling structure present in the labels. A key challenge is developing tractable models thatâ€¦ (More)