Gal Hyams
Tel Aviv University
8 Papers
19 Citations
Gal Hyams is an academic researcher from Tel Aviv University. The author has contributed to research in topics: MNIST database & Medicine. The author has an hindex of 3, co-authored 5 publications.
Chat about Author
Papers
Multi-Knock—a multi-targeted genome-scale CRISPR toolbox to overcome functional redundancy in plants
Yangjie Hu,Priyanka Patra,Odelia Pisanty,Anatoly Yu. Shafir,Zeinu Mussa Belew,Jenia Binenbaum,Bihai Shi,Laurence Charrier,Gal Hyams,Yuqin Zhang,Daniela Weiss,Christoph Crocoll,Adi Avni,Teva Vernoux,Markus Geisler,Hussam Hassan Nour-Eldin,Itay Mayrose,Eilon Shani +17 more
TL;DR: MultiKnock as discussed by the authors is a genome-scale clustered regularly interspaced short palindromic repeat toolbox that overcomes functional redundancy in Arabidopsis by simultaneously targeting multiple gene-family members, thus identifying genetically hidden components.
•Posted Content
Improved Training for Self-Training by Confidence Assessments
TL;DR: Using credible interval based on MC-dropout as a confidence measure, the proposed method is able to gain substantially better results comparing to several other pseudo-labeling methods and out-performs the former state-of-the-art pseudo- labeling technique by 7\(\%\) on the MNIST dataset.
12
Improved Training for Self Training by Confidence Assessments
Dor Bank,Daniel Greenfeld,Gal Hyams +2 more
- 10 Jul 2018
TL;DR: In this article, the authors proposed a self-training method based on MC-dropout as a confidence measure, which is able to gain substantially better results comparing to several other pseudo-labeling methods and out-performs the former state-of-the-art pseudo-labeling technique by 7\(\%) on the MNIST dataset.
10
CRISPys: Optimal sgRNA design for editing multiple members of a gene family using the CRISPR system
TL;DR: CRISPys harnesses the lack of specificity of the CRISPR-Cas9 genome editing technique, providing researchers the ability to simultaneously mutate multiple genes and outperforms existing approaches that are based on simple alignment of the input gene family.
•Posted Content
Improved Training for Self-Training.
Gal Hyams,Daniel Greenfeld,Dor Bank +2 more
- 30 Sep 2017
TL;DR: This work examined learning methods from unlabeled data after an initial training on a limited labeled data set and suggested approaches were applied on the MNIST data- set as a proof of concept for a vision classification task and on the ADE20K data-set in order to tackle the semi-supervised semantic segmentation problem.
3