ML Anthology

Lifelong Perceptual Programming by Example

Alexander L. Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow
ICLR 2017
/iclr/2017/gaunt2017iclr-lifelong/

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.

PDF ICLR Semantic Scholar

Cite

Text

Gaunt et al. "Lifelong Perceptual Programming by Example." International Conference on Learning Representations, 2017.

Markdown

[Gaunt et al. "Lifelong Perceptual Programming by Example." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/gaunt2017iclr-lifelong/)

BibTeX

@inproceedings{gaunt2017iclr-lifelong,
  title     = {{Lifelong Perceptual Programming by Example}},
  author    = {Gaunt, Alexander L. and Brockschmidt, Marc and Kushman, Nate and Tarlow, Daniel},
  booktitle = {International Conference on Learning Representations},
  year      = {2017},
  url       = {https://mlanthology.org/iclr/2017/gaunt2017iclr-lifelong/}
}