Daitan is proud to announce that at the Ninth International Conference on Learning Representations (ICLR) our Data Scientist, Thalles Santos SIlva is presenting (virtually) the paper titled, Consistent Assignment for Representation Learning,  which is being held during the Energy Based Models Workshop session at ICLR2021 on May 7th, 2021.

The presentation introduces Consistent Assignment for Representation Learning (CARL); an unsupervised learning method to learn visual representations by combining contrastive learning with deep clustering. The approach for using CARL versus contemporary work on contrastive learning and associated results are discussed during the session.  The presentation abstract can be found here where the full research article can also be accessed.

The International Conference on Learning Representations (ICLR) is a well established, prestigious gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning.

ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.

About Daitan

Daitan has been helping global enterprises build core technology, data solutions, and software products since 2004. Companies of all sizes trust Daitan to deliver solutions that accelerate growth, lower costs, improve profitability, and reduce execution risk.