Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-code-9

Program induction

3260 papers • 126 benchmarks • 313 datasets

Generating program code for domain-specific tasks

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in program-induction-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find program-induction-9 models and implementations

Datasets

AQUA-RAT

Subtasks

No subtasks available.

Most implemented papers

DeepProbLog: Neural Probabilistic Logic Programming

Sebastijan Dumancic, Angelika Kimmig, T. Demeester, Robin Manhaeve, L. D. Raedt•Mon Apr 30 2018

This work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that exploits the full expressiveness and strengths of both worlds and can be trained end-to-end based on examples.

672

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

RobustFill: Neural Program Learning under Noisy I/O

Pushmeet Kohli, Jacob Devlin, Abdel-rahman Mohamed, Jonathan Uesato, Surya Bhupatiraju, Rishabh Singh•Mon Mar 20 2017

This work directly compares both approaches for automatic program learning on a large-scale, real-world learning task and demonstrates that the strength of each approach is highly dependent on the evaluation metric and end-user application.

409 0

Paper Graph

Learning a Natural Language Interface with Neural Programmer

Quoc V. Le, Martín Abadi, A. McCallum, Dario Amodei, Arvind Neelakantan•Thu Nov 03 2016

This paper presents the first weakly supervised, end-to-end neural network model to induce such programs on a real-world dataset, and enhances the objective function of Neural Programmer, a neural network with built-in discrete operations, and applies it on WikiTableQuestions, a natural language question-answering dataset.

138 0

Paper Graph

Forgetting to learn logic programs

Andrew Cropper•Thu Nov 14 2019

This work considers forgetting in an inductive logic programming (ILP) setting and shows that forgetting can significantly reduce both the size of the hypothesis space and the sample complexity of an ILP learner.

16 0

Paper Graph

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks

S. Savarese, Li Fei-Fei, Suraj Nair, Yuke Zhu, Animesh Garg, Danfei Xu, J. Gao•Tue Oct 03 2017

A novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction, and achieves strong generalization across sequential tasks that exhibit hierarchal and compositional structures.

209 0

Paper Graph

Recent Advances in Neural Program Synthesis

Neel Kant•Tue Feb 06 2018

This paper examines the fascinating evolution of program induction models, along with how they have succeeded, failed and been reimagined since, and takes a contrastive look at program synthesis.

38 0

Paper Graph

Playgol: learning programs through play

Andrew Cropper•Wed Apr 17 2019

The idea of playing (or, more verbosely, unsupervised bootstrapping for supervised program induction) is an important contribution to the problem of developing program induction approaches that self-discover BK.

36 0

Paper Graph

Adding a benchmark result helps the community track progress.

Program induction | State-of-the-Art