Zobrazeno 1 - 10
of 538
pro vyhledávání: '"A. Brockschmidt"'
Autor:
Klein, Leon, Foong, Andrew Y. K., Fjelde, Tor Erlend, Mlodozeniec, Bruno, Brockschmidt, Marc, Nowozin, Sebastian, Noé, Frank, Tomioka, Ryota
Molecular dynamics (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion are integrated with timesteps on the order of femtoseconds ($1\textrm{fs}=10^{-15}\textrm{
Externí odkaz:
http://arxiv.org/abs/2302.01170
Learning program semantics from raw source code is challenging due to the complexity of real-world programming language syntax and due to the difficulty of reconstructing long-distance relational information implicitly represented in programs using i
Externí odkaz:
http://arxiv.org/abs/2206.06986
Learning from structured data is a core machine learning task. Commonly, such data is represented as graphs, which normally only consider (typed) binary relationships between pairs of nodes. This is a substantial limitation for many domains with high
Externí odkaz:
http://arxiv.org/abs/2201.12113
Autor:
Guo, Daya, Svyatkovskiy, Alexey, Yin, Jian, Duan, Nan, Brockschmidt, Marc, Allamanis, Miltiadis
Code completion is usually cast as a language modelling problem, i.e., continuing an input in a left-to-right fashion. However, in practice, some parts of the completion (e.g., string literals) may be very hard to predict, whereas subsequent parts di
Externí odkaz:
http://arxiv.org/abs/2106.10158
Machine learning-based program analyses have recently shown the promise of integrating formal and probabilistic reasoning towards aiding software development. However, in the absence of large annotated corpora, training these analyses is challenging.
Externí odkaz:
http://arxiv.org/abs/2105.12787
Autor:
Maziarz, Krzysztof, Jackson-Flux, Henry, Cameron, Pashmina, Sirockin, Finton, Schneider, Nadine, Stiefl, Nikolaus, Segler, Marwin, Brockschmidt, Marc
Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery. A plethora of generative models is available, building molecules either atom-by-atom and bond-by-bond or fragment-by-fragment. However, m
Externí odkaz:
http://arxiv.org/abs/2103.03864
Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue that common seq2seq models (with a facility to copy single tokens) are
Externí odkaz:
http://arxiv.org/abs/2006.04771
Autor:
Zanella-Béguelin, Santiago, Wutschitz, Lukas, Tople, Shruti, Rühle, Victor, Paverd, Andrew, Ohrimenko, Olga, Köpf, Boris, Brockschmidt, Marc
To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update can reveal
Externí odkaz:
http://arxiv.org/abs/1912.07942
We present a technique to infer lower bounds on the worst-case runtime complexity of integer programs, where in contrast to earlier work, our approach is not restricted to tail-recursion. Our technique constructs symbolic representations of program e
Externí odkaz:
http://arxiv.org/abs/1911.01077
While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real-world g
Externí odkaz:
http://arxiv.org/abs/1910.05639