no code implementations • 17 Nov 2019 • Haw-Shiuan Chang, Shankar Vembu, Sunil Mohan, Rheeya Uppaal, Andrew McCallum
Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks.
1 code implementation • 24 Jul 2016 • Shankar Vembu, Sandra Zilles
Interactive learning is a process in which a machine learning algorithm is provided with meaningful, well-chosen examples as opposed to randomly chosen examples typical in standard supervised learning.
no code implementations • 11 Aug 2014 • Amit G. Deshwar, Shankar Vembu, Quaid Morris
Statistical machine learning methods, especially nonparametric Bayesian methods, have become increasingly popular to infer clonal population structure of tumors.
no code implementations • 27 Jun 2014 • Amit G. Deshwar, Shankar Vembu, Christina K. Yung, Gun Ho Jang, Lincoln Stein, Quaid Morris
Tumors often contain multiple subpopulations of cancerous cells defined by distinct somatic mutations.
no code implementations • 11 Oct 2012 • Wei Jiao, Shankar Vembu, Amit G. Deshwar, Lincoln Stein, Quaid Morris
High-throughput sequencing allows the detection and quantification of frequencies of somatic single nucleotide variants (SNV) in heterogeneous tumor cell populations.