Program induction

20 papers with code • 0 benchmarks • 1 datasets

Generating program code for domain-specific tasks

Datasets


Most implemented papers

RobustFill: Neural Program Learning under Noisy I/O

amitz25/PCCoder ICML 2017

Recently, two competing approaches for automatic program learning have received significant attention: (1) neural program synthesis, where a neural network is conditioned on input/output (I/O) examples and learns to generate a program, and (2) neural program induction, where a neural network generates new outputs directly using a latent program representation.

Learning a Natural Language Interface with Neural Programmer

tensorflow/models 28 Nov 2016

The main experimental result in this paper is that a single Neural Programmer model achieves 34. 2% accuracy using only 10, 000 examples with weak supervision.

DeepProbLog: Neural Probabilistic Logic Programming

MarcRoigVilamala/DeepProbCEP NeurIPS 2018

We introduce DeepProbLog, a probabilistic logic programming language that incorporates deep learning by means of neural predicates.

Forgetting to learn logic programs

metagol/metagol 15 Nov 2019

To improve learning performance, we explore the idea of forgetting, where a learner can additionally remove programs from its BK.

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning

CatherineWong/dreamcoder 15 Jun 2020

It builds expertise by creating programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages.

Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

deepmind/AQuA 11 May 2017

Solving algebraic word problems requires executing a series of arithmetic operations---a program---to obtain a final answer.

P-Tree Programming

coesch/ptree 12 Jul 2017

From this prototype tree we form program instances which we evaluate on a given problem.

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks

StanfordVL/arxivbot 4 Oct 2017

In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction.

Recent Advances in Neural Program Synthesis

qu-arx/arx-inf 7 Feb 2018

In recent years, deep learning has made tremendous progress in a number of fields that were previously out of reach for artificial intelligence.

Playgol: learning programs through play

metagol/metagol 18 Apr 2019

In this approach, a program induction system (the learner) is given a set of tasks and initial background knowledge.