Lecture 1: Learning with Linear Models (Mário Figueiredo)
Краткое объяснение больших языковых моделей
CEG3011(2025) - Lecture 8
Talk: Reality Checks (Kyunghyun Cho)
LxMLS 2024
Gated KalmaNet: слой с затуханием памяти, использующий регрессию гребня во время тестирования — А...
Новый код — Шон Гроув, OpenAI
Talk: Musings on Direct Preference Optimization (Kyunghyun Cho)
Но что такое нейронная сеть? | Глава 1. Глубокое обучение
Neural networks
Lecture 5: Causality (Adèle Ribeiro)
Lecture 6: Causality (Adèle Ribeiro)
Ex-OpenAI Scientist WARNS: "You Have No Idea What's Coming"
Conway's Base 13 Function - Numberphile
Talk: Changing Space of Optimization (Sara Hooker)
NVIDIA CEO Jensen Huang's Vision for the Future
Talk: The Search for Foundations in AI Interpretability (Maxime Peyrard)
Lecture 4: Transformers and Large Pretrained Models (Sweta Agrawal)
Talk: Structured State Space Models for Deep Sequence Modeling (Albert Gu)
Andrej Karpathy: Software Is Changing (Again)