Recent Advances in Neural Program Synthesis
arXiv:1802.02353
Abstract
In recent years, deep learning has made tremendous progress in a number of fields that were previously out of reach for artificial intelligence. The successes in these problems has led researchers to consider the possibilities for intelligent systems to tackle a problem that humans have only recently themselves considered: program synthesis. This challenge is unlike others such as object recognition and speech translation, since its abstract nature and demand for rigor make it difficult even for human minds to attempt. While it is still far from being solved or even competitive with most existing methods, neural program synthesis is a rapidly growing discipline which holds great promise if completely realized. In this paper, we start with exploring the problem statement and challenges of program synthesis. Then, we examine the fascinating evolution of program induction models, along with how they have succeeded, failed and been reimagined since. Finally, we conclude with a contrastive look at program synthesis and future research recommendations for the field.
arXiv comment16 pages (without citations); Literature Review
References in corpus (12)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Neural Architecture Search with Reinforcement Learning
- VQA: Visual Question Answering
- Learning Combinatorial Optimization Algorithms over Graphs
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- DeepCoder: Learning to Write Programs
- Neural GPUs Learn Algorithms
- Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
- Neuro-Symbolic Program Synthesis
- Making Neural Programming Architectures Generalize via Recursion
- TerpreT: A Probabilistic Programming Language for Program Induction
- Towards Synthesizing Complex Programs from Input-Output Examples
Cited by in corpus (9)
- Neural Shuffle-Exchange Networks -- Sequence Processing in O(n log n) Time
- Neural Inverse Knitting: From Images to Manufacturing Instructions
- ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
- Language (Re)modelling: Towards Embodied Language Understanding
- Neural Program Synthesis By Self-Learning
- BF++: a language for general-purpose program synthesis
- Understanding in Artificial Intelligence
- Formal Fields: A Framework to Automate Code Generation Across Domains
- Type-driven Neural Programming by Example