How To Perform Similarity Search for Few Shot Training

Associative Based Similarity Search for Few Shot Training

Presented By Dr. Avidan Akerib
Dr. Avidan Akerib
Dr. Avidan Akerib
VP Associative Computing, GSI Technology

Dr. Avidan Akerib is the VP of GSI Technology's Associative Computing Business Unit. He has over 30 years of experience in parallel computing and In-Place Associative Computing. He has over 25 Granted Patents related to parallel and in-memory associative computing. Dr. Akerib has a PhD in Applied Mathematics & Computer Science from the Weismann Instiitute of Science, Israel.

His specialties are Computational Memory, Associative Processing, Parallel Algorithms, and Machine Learning.

Presentation Description

Conventional CNNs require a finite number of pre-known classes with many examples. In this webinar, we present an associative computing approach and chip architecture for Few Shot training networks using O (1) similarity search and Top K computing. This approach enables only few examples per label, extreme classification and fast adjustment.

Presentation Curriculum

Webinar Information
Hide Content