As the 2010’s draw to a close , it’s worth taking a look back at the monumental progress that has been made in Deep Learning in this decade.[1] Dr

The Decade of Deep Learning | Leo Gao

submited by

Style Pass

2021-07-09 03:00:06

As the 2010’s draw to a close , it’s worth taking a look back at the monumental progress that has been made in Deep Learning in this decade.[1] Driven by the development of ever-more powerful compute and the increased availability of big data, Deep Learning has successfully tackled many previously intractable problems, especially in Computer Vision and Natural Language Processing. Deep Learning has also begun to see real-world application everywhere around us, from the high-impact to the frivolous, from autonomous vehicles and medical imaging to virtual assistants and deepfakes.

This post is an overview of some the most influential Deep Learning papers of the last decade. My hope is to provide a jumping-off point into many disparate areas of Deep Learning by providing succinct and dense summaries that go slightly deeper than a surface level exposition, with many references to the relevant resources.

Given the nature of research, assigning credit is very difficult—the same ideas are pursued by many simultaneously, and the most influential paper is often neither the first nor the best. I try my best to tiptoe the line between influence and first/best works by listing the most influential papers as main entries and the other relevant papers that precede or improve upon the main entry as honorable mentions.[2] Of course, as such a list will always be subjective, this is not meant to be final, exhaustive, or authoritative. If you feel that the ordering, omission, or description of any paper is incorrect, please let me know—I would be more than glad to improve this list by making it more complete and accurate.