Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Lifelong Perceptual Programming By Example
Alexander L. Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow
Feb 17, 2017 (modified: Feb 17, 2017)ICLR 2017 workshop submissionreaders: everyone
Abstract:We introduce and develop solutions for the problem of Lifelong Perceptual Programming By Example (LPPBE). The problem is to induce a series of programs that require understanding perceptual data like images or text. LPPBE systems learn from weak supervision (input-output examples) and incrementally construct a shared library of components that grows and improves as more tasks are solved. Methodologically, we extend differentiable interpreters to operate on perceptual data and to share components across tasks. Empirically we show that this leads to a lifelong learning system that transfers knowledge to new tasks more effectively than baselines, and the performance on earlier tasks continues to improve even as the system learns on new, different tasks.
TL;DR:Combination of differentiable interpreters and neural networks for lifelong learning of a model composed of neural and source code functions
Keywords:Supervised Learning, Deep learning
Enter your feedback below and we'll get back to you as soon as possible.