Join us for an insightful talk by Hrant Khachatrian, 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 is required to secure your spot.