Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Bieber, David"'
Autor:
Bieber, David, Shi, Kensen, Maniatis, Petros, Sutton, Charles, Hellendoorn, Vincent, Johnson, Daniel, Tarlow, Daniel
Graph representations of programs are commonly a central element of machine learning for code research. We introduce an open source Python library python_graphs that applies static analysis to construct graph representations of Python programs suitab
Externí odkaz:
http://arxiv.org/abs/2208.07461
Autor:
Dohan, David, Xu, Winnie, Lewkowycz, Aitor, Austin, Jacob, Bieber, David, Lopes, Raphael Gontijo, Wu, Yuhuai, Michalewski, Henryk, Saurous, Rif A., Sohl-dickstein, Jascha, Murphy, Kevin, Sutton, Charles
Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are probabilistic model
Externí odkaz:
http://arxiv.org/abs/2207.10342
The execution behavior of a program often depends on external resources, such as program inputs or file contents, and so cannot be run in isolation. Nevertheless, software developers benefit from fast iteration loops where automated tools identify er
Externí odkaz:
http://arxiv.org/abs/2203.03771
Autor:
Nye, Maxwell, Andreassen, Anders Johan, Gur-Ari, Guy, Michalewski, Henryk, Austin, Jacob, Bieber, David, Dohan, David, Lewkowycz, Aitor, Bosma, Maarten, Luan, David, Sutton, Charles, Odena, Augustus
Large pre-trained language models perform remarkably well on tasks that can be done "in one pass", such as generating realistic text or synthesizing computer programs. However, they struggle with tasks that require unbounded multi-step computation, s
Externí odkaz:
http://arxiv.org/abs/2112.00114
Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and program repair. They benefit from leveraging program structure like control flow graphs, but they are not
Externí odkaz:
http://arxiv.org/abs/2010.12621
Program synthesis is challenging largely because of the difficulty of search in a large space of programs. Human programmers routinely tackle the task of writing complex programs by writing sub-programs and then analyzing their intermediate results t
Externí odkaz:
http://arxiv.org/abs/2007.14381
The success and popularity of deep learning is on the rise, partially due to powerful deep learning frameworks such as TensorFlow and PyTorch that make it easier to develop deep learning models. However, these libraries also come with steep learning
Externí odkaz:
http://arxiv.org/abs/2003.09040
Sampling is a fundamental technique, and sampling without replacement is often desirable when duplicate samples are not beneficial. Within machine learning, sampling is useful for generating diverse outputs from a trained model. We present an elegant
Externí odkaz:
http://arxiv.org/abs/2002.09067
Programming languages are emerging as a challenging and interesting domain for machine learning. A core task, which has received significant attention in recent years, is building generative models of source code. However, to our knowledge, previous
Externí odkaz:
http://arxiv.org/abs/1904.02818
Due to its potential to improve programmer productivity and software quality, automated program repair has been an active topic of research. Newer techniques harness neural networks to learn directly from examples of buggy programs and their fixes. I
Externí odkaz:
http://arxiv.org/abs/1904.01720