Join us at ML OpenTalk February 2025 for an insightful talk by Hrant Khachatrian. He is the director of one of our communities, YerevaNN , and ML Research Group Lead at Yerevan State University!

Topics to be covered:

– Kaplan & Chinchilla Scaling Laws: How our understanding of compute-optimal scaling has evolved.
– Predicting Downstream Task Accuracy: Using scaling laws to estimate performance on real-world tasks.
– Multi-Epoch Training Effects: How training beyond a single epoch modifies scaling dynamics.
– Scaling Laws for Inference: Understanding latency, memory, and compute costs at deployment.
– Our Experience in Molecules and Images: Applying scaling laws in domain-specific AI research.

This event is perfect for machine learning professionals and anyone interested in ML industry trends.

Date: February 13
Time: 19:00-21:00
Venue: Yandex Hall, Moskovyan 35, Yerevan
Language: English

Registration for ML OpenTalk February 2025 is required to secure your spot.

Established in 2016, at the YerevaNN Scientific-Educational Foundation (YerevaNN), a non-profit computer science research center, we are enabling an ML world-class research in Machine Learning (ML) in Armenia.

The mission of YerevaNN is to stimulate scientific careers in computer science and to facilitate the growth of the next generation of computer science professors in Armenia. YerevaNN succeeds with its mission by building a research-friendly environment for early-career computer scientists and setting up collaborations with the world’s leading labs.