February 22-24, 2023
Montreal, Canada

The future of Artificial Intelligence is contrastive

Applying AI to real world problems in a supervised fashion requires large set of data covering all aspects of the problem we are solving. In reality, it’s impossible to build such dataset thus giving our model limited understanding of the problem leading to absurd predictions. The solution is Contrastive Learning which learns similarities and differences by contrasting samples against each other therefore limiting the need for human supervision.

View all 155 sessions

Ahmed Touila

DiliTrust

Lead AI research at DiliTrust. Building machine learning pipelines for contract analysis from R&D to production deployment. I'm currently leading DiliTrust's R&D team to improve our product and introduce new AI based features while exploring and advancing state of the art approaches in the legal domain.

Read More