[Turkmath:7056] Gebze Teknik Üniversitesi Matematik Bölümü Genel Seminerleri

[GTU Mathematics]

 Sayin Liste Uyeleri,

Gebze Teknik Üniversitesi (GTU) Matematik Bölümü Genel Seminerleri
kapsamında, 7 Mart Cuma günü saat 14:00'te Dr. Berkay Anahtarcı (Özyeğin
Üniversitesi) bir seminer verecektir. Seminerin detayları aşağıda olup tüm
ilgilenenler davetlidir.

Saygılarımızla.

Dear all,

There will be a seminar in Gebze Technical University (GTU) on 7th of March
by Dr. Berkay Anahtarcı (University of Özyeğin).

Time and place: At 14:00 in Department of Mathematics, Lecture Amphi 2

Title:  The Mathematics Behind the DeepSeek Model
Abstract:   This talk explores the mathematical underpinnings of DeepSeek
R1, a reinforcement learning model tailored for complex reasoning. Unlike
conventional supervised fine-tuning approaches, DeepSeek R1 leverages Group
Relative Policy Optimization (GRPO), an innovative technique that refines
Proximal Policy Optimization (PPO) by eliminating the need for a critic.
GRPO enhances chain-of-thought reasoning by structuring problem-solving
into sequential steps. Through an analytical perspective, we will examine
the theoretical properties of GRPO.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://yunus.listweb.bilkent.edu.tr/pipermail/turkmath/attachments/20250303/76a53851/attachment.html>