Live with Jay Alammar, Josh Starmer, and Luis Serrano Direct Preference Optimization (DPO) - How to fine-tune LLMs directly without reinforcement learning KL Divergence - How to tell how different two distributions are Newton's method for approximating zeros of polynomials - Math for ML with Deeplearning.ai 4d | Louis Serano The Stone-Weierstrass Theorem - How to approximate functions 12d | Louis Serano Keys, Queries, and Values: The celestial mechanics of attention 19d | Louis Serano Why is ChatGPT so bad at telling jokes (yet so good at writing poems?) 21d | Louis Serano Why is DeepSeek so good? 29d | Louis Serano Universal Approximation Theorem - The Fundamental Building Block of Deep Learning 2mo | Louis Serano Happy 2025, and thank you for your support! 2mo | Louis Serano The Kolmogorov-Arnold Theorem 3mo | Louis Serano Kolmogorov-Arnold Networks (KANs) - What are they and how do they work? 3mo | Louis Serano Live with Jay Alammar, Josh Starmer, and Luis Serrano 4mo | Louis Serano 1 2 3 4 5 > >> Join group Members Search CreatedPast one dayPast four dayPast month Choose a GroupLouis Serano Choose a User Sort byby relevanceUpvotedNew firstBookmark countComment count Search