Neurosymbolic programming

S Chaudhuri, K Ellis, O Polozov, R Singh… - … and Trends® in …, 2021 - nowpublishers.com
We survey recent work on neurosymbolic programming, an emerging area that bridges the
areas of deep learning and program synthesis. Like in classic machine learning, the goal …

[HTML][HTML] The child as hacker

JS Rule, JB Tenenbaum, ST Piantadosi - Trends in cognitive sciences, 2020 - cell.com
The scope of human learning and development poses a radical challenge for cognitive
science. We propose that developmental theories can address this challenge by adopting …

Codegeex: A pre-trained model for code generation with multilingual benchmarking on humaneval-x

Q Zheng, X ** inductive program synthesis with wake-sleep library learning
K Ellis, C Wong, M Nye, M Sablé-Meyer… - Proceedings of the …, 2021 - dl.acm.org
We present a system for inductive program synthesis called DreamCoder, which inputs a
corpus of synthesis problems each specified by one or a few examples, and automatically …

The next decade in AI: four steps towards robust artificial intelligence

G Marcus - arxiv preprint arxiv:2002.06177, 2020 - arxiv.org
Recent research in artificial intelligence and machine learning has largely emphasized
general-purpose learning and ever-larger training sets and more and more compute. In …

Is self-repair a silver bullet for code generation?

TX Olausson, JP Inala, C Wang, J Gao… - arxiv preprint arxiv …, 2023 - arxiv.org
Large language models have shown remarkable aptitude in code generation, but still
struggle to perform complex tasks. Self-repair--in which the model debugs and repairs its …

Automl-zero: Evolving machine learning algorithms from scratch

E Real, C Liang, D So, Q Le - International conference on …, 2020 - proceedings.mlr.press
Abstract Machine learning research has advanced in multiple aspects, including model
structures and learning methods. The effort to automate such research, known as AutoML …

Algo: Synthesizing algorithmic programs with generated oracle verifiers

K Zhang, D Wang, J **a… - Advances in Neural …, 2023 - proceedings.neurips.cc
Large language models (LLMs) excel at implementing code from functionality descriptions
but struggle with algorithmic problems that require not only implementation but also …