The Three Pillars of Machine Programming
arXiv:1803.07244
Abstract
In this position paper, we describe our vision of the future of machine programming through a categorical examination of three pillars of research. Those pillars are: (i) intention, (ii) invention, and(iii) adaptation. Intention emphasizes advancements in the human-to-computer and computer-to-machine-learning interfaces. Invention emphasizes the creation or refinement of algorithms or core hardware and software building blocks through machine learning (ML). Adaptation emphasizes advances in the use of ML-based constructs to autonomously evolve software.
References in corpus (13)
- TensorFlow: A system for large-scale machine learning
- HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
- SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
- DeepCoder: Learning to Write Programs
- Making Neural Programming Architectures Generalize via Recursion
- The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox
- Tree-to-tree Neural Networks for Program Translation
- TerpreT: A Probabilistic Programming Language for Program Induction
- Learning to Infer Graphics Programs from Hand-Drawn Images
- Towards Synthesizing Complex Programs from Input-Output Examples
- Neural Program Synthesis with Priority Queue Training
- AI Programmer: Autonomously Creating Software Programs Using Genetic Algorithms
- Asynchronous Complex Analytics in a Distributed Dataflow Architecture