J
Jerry Ma
Researcher at Facebook
Publications - 16
Citations - 2078
Jerry Ma is an academic researcher from Facebook. The author has contributed to research in topics: Deep learning & Password. The author has an hindex of 12, co-authored 15 publications receiving 800 citations. Previous affiliations of Jerry Ma include Yale University & United States Naval Research Laboratory.
Papers
More filters
Posted ContentDOI
Biological Structure and Function Emerge from Scaling Unsupervised Learning to 250 Million Protein Sequences
Alexander Rives,Siddharth Goyal,Joshua Meier,Demi Guo,Myle Ott,C. Lawrence Zitnick,Jerry Ma,Rob Fergus,Rob Fergus +8 more
TL;DR: This work uses unsupervised learning to train a deep contextual language model on 86 billion amino acids across 250 million protein sequences spanning evolutionary diversity, enabling state-of-the-art supervised prediction of mutational effect and secondary structure, and improving state- of- the-art features for long-range contact prediction.
Journal ArticleDOI
Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
Alexander Rives,Alexander Rives,Joshua Meier,Tom Sercu,Siddharth Goyal,Zeming Lin,Jason Liu,Demi Guo,Myle Ott,C. Lawrence Zitnick,Jerry Ma,Jerry Ma,Rob Fergus +12 more
TL;DR: This paper used unsupervised learning to train a deep contextual language model on 86 billion amino acids across 250 million protein sequences spanning evolutionary diversity, which contains information about biological properties in its representations.
Proceedings ArticleDOI
A Study of Probabilistic Password Models
TL;DR: In this paper, a systematic evaluation of a large number of probabilistic password models, including Markov models using different normalization and smoothing methods, and found that, among other things, when done correctly, they perform significantly better than the Probabilistic Context-Free Grammar model proposed in Weir et al., which has been used as the state of the art password model in recent research.
Posted Content
Quasi-hyperbolic momentum and Adam for deep learning
Jerry Ma,Denis Yarats +1 more
TL;DR: In this article, a quasi-hyperbolic momentum algorithm (QHM) is proposed to accelerate SGD. But the algorithm is not suitable for deep learning, as it requires a large number of SGD steps.
Posted Content
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
Yuandong Tian,Jerry Ma,Qucheng Gong,Shubho Sengupta,Zhuoyuan Chen,James Pinkerton,C. Lawrence Zitnick +6 more
TL;DR: ELF OpenGo is the first open-source Go AI to convincingly demonstrate superhuman performance with a perfect (20:0) record against global top professionals and is proposed, anopen-source reimplementation of the AlphaZero algorithm.