Marc Brockschmidt

Summary - TerpreT: A Probabilistic Programming Language for Program Induction

2016 · arXiv (Cornell University)

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 is TerpreT, a domain-specific language for expressing program synthesis …

Differentiable Programs with Neural Libraries

2016 · arXiv (Cornell University)

We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write interpretable algorithms with perceptual components. We explore the benefits of inductive …

Exploring Representation of Horn Clauses using GNNs (Extended Technical Report)

2022 · arXiv (Cornell University)

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 identifiers. Addressing …

Structured Neural Summarization

2018 · arXiv (Cornell University)

Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, …