UCL Discovery (University College London) · 2017 · 58 citations · 22 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningNatural Language ProcessingDeep LearningInterpreter DesignNatural Language UnderstandingNeural NetworksConvolutional Neural NetworksGradient DescentPrior Related KnowledgeProcedural KnowledgeRecurrent Neural Networks
Given that in practice training data is scarce for all but a small set of problems, a core question is how to incorporate prior knowledge into a model. In this paper, we consider the case of prior procedural knowledge for neural networks, such as knowing how a program should traverse a sequence, but not what local actions should be performed at each step. To this end, we present an end-to-end differentiable interpreter for the programming language Forth which enables programmers to write program sketches with slots that can be filled with behaviour trained from program input-output data. We can optimise this behaviour directly through gradient descent techniques on user-specified objectives, and also integrate the program into any larger neural computation graph. We show empirically that our interpreter is able to effectively leverage different levels of prior program structure and learn complex behaviours such as sequence sorting and addition. When connected to outputs of an LSTM and trained jointly, our interpreter achieves state-of-the-art accuracy for end-to-end reasoning about quantities expressed in natural language stories.
22
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le · arXiv (Cornell University) · 2014 · 3.5K citations · Full text
Computing, Computer Science, French +14
Symbolic execution and program testing
James C. King · Communications of the ACM · 1976 · 3K citations · Full text
Hybrid computing using a neural network with dynamic external memory
Alex Graves, Greg Wayne, Malcolm Reynolds et al. · Nature · 2016 · 1.4K citations
Combinatorial sketching for finite programs
Armando Solar-Lezama, Liviu Tancau, Rastislav Bodík et al. · 2006 · 642 citations