https://trishul.us/wp-content/uploads/2021/10/image_part_010.jpeg 455 620 Academic Web Pages /wp-content/themes/awp-enfold/blank.png Academic Web Pages2021-10-26 15:04:122021-12-02 10:28:10Data-Efficient Learning
Humans are frequently able to learn new skills from just a few examples. In contrast, modern learning algorithms can be tremendously data-hungry. We have been exploring ways to overcome this shortcoming of machine learning through a combination of symbolic and statistical techniques.
As a concrete example, some of our recent work uses program synthesis to automatically compose a set of previously learned neural library modules. The composite models are fine-tuned on new tasks, and this fine-tuning takes many fewer examples than learning from scratch. Our longer-term goals include scaling such compositional program synthesis to larger libraries and much larger modules (think GPT-3), and discovering libraries in an unsupervised manner.