swMATH ID: 46010
Software Authors: Devlin, Jacob; Uesato, Jonathan; Bhupatiraju, Surya; Singh, Rishabh; Mohamed, Abdel-rahman; Kohli, Pushmeet
Description: RobustFill: Neural Program Learning under Noisy I/O. The problem of automatically generating a computer program from some specification has been studied since the early days of AI. 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. Here, for the first time, we directly compare both approaches on a large-scale, real-world learning task. We additionally contrast to rule-based program synthesis, which uses hand-crafted semantics to guide the program generation. Our neural models use a modified attention RNN to allow encoding of variable-sized sets of I/O pairs. Our best synthesis model achieves 92
Homepage: https://arxiv.org/abs/1703.07469
Source Code:  https://github.com/yeoedward/Robust-Fill
Dependencies: Python
Related Software: SQLizer; Push; PyshGP; PushGP; PyGGI; Gin; SpreadsheetCoder; DeepCoder; GenProg; PonyGE2; NLTK; aplore3; Prophet; Python; Holophrasm; E Theorem Prover; GamePad; NeuroSAT; Adam; TensorFlow
Cited in: 5 Documents

Citations by Year