Adi
Zicher (Kadoche)

Critical Decisions Using Data Science in Production

 

Adi Zicher (Kadoche)

Adi
Zicher
(Kadoche)

Critical Decisions Using Data Science in Production

 

Adi Zicher (Kadoche)

Bio

Adi started her military service in 2011 in Talpiot elite program. During the 3 year course, she completed her BSc in computer science and physics at the Hebrew University. In 2014, she started a 2.5 year job as an algorithmic researcher in IAF, where she developed CV algorithms and classic algorithms (tailor-made). During those years, she completed her MSc in electrical engineering from Tel Aviv University, graduating 1st in class.

 

Following her studies, she served as IAF’s data science team leader, and a year ago she took on her current role as a Data Science Strategic Leader – responsible for CV projects, and for leading the methodology and strategy of the IDF in the Data Science and AI field.

Bio

Adi started her military service in 2011 in Talpiot elite program. During the 3 year course, she completed her BSc in computer science and physics at the Hebrew University. In 2014, she started a 2.5 year job as an algorithmic researcher in IAF, where she developed CV algorithms and classic algorithms (tailor-made). During those years, she completed her MSc in electrical engineering from Tel Aviv University, graduating 1st in class.


Following her studies, she served as IAF’s data science team leader, and a year ago she took on her current role as a Data Science Strategic Leader – responsible for CV projects, and for leading the methodology and strategy of the IDF in the Data Science and AI field.

Abstract

As time goes by, we see more and more algorithms in the heart of critical systems, where each decision matters and has significant meaning, with minimum tolerance to mistakes. We, the data scientists, know the big potential in AI, that can empower our processes and decisions. But how do we make our algorithms strong enough to handle very complex problems in a changing environment, with high confidence and high quality?

Abstract

As time goes by, we see more and more algorithms in the heart of critical systems, where each decision matters and has significant meaning, with minimum tolerance to mistakes. We, the data scientists, know the big potential in AI, that can empower our processes and decisions. But how do we make our algorithms strong enough to handle very complex problems in a changing environment, with high confidence and high quality?

Discussion Points

  • First, how to decide whether a labeled data is a must? 
  • Different types of labeling challenges we’ve dealt with as data scientists (partial labels, noisy labels, etc.)
  • Academic approaches that discuss possible solutions to these problems
  • Practical solutions we eventually implemented 
  • Interesting case studies and results

Discussion Points

  • First, how to decide whether a labeled data is a must? 
  • Different types of labeling challenges we’ve dealt with as data scientists (partial labels, noisy labels, etc.)
  • Academic approaches that discuss possible solutions to these problems
  • Practical solutions we eventually implemented 
  • Interesting case studies and results

Planned Agenda

Planned Agenda