Dynamic Neural Networks
Joey discusses the challenges of predicting human behavior in autonomous driving, emphasizing the potential of general foundation models trained on diverse data sources. He also highlights the need for neural networks to process data more dynamically, suggesting that smarter model-switching could enhance conversational AI by optimizing computational resources based on the complexity of the task at hand.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
707: Vicuña, Gorilla, Chatbot Arena and Socially Beneficial LLMs — with Prof. Joey Gonzalez
Related Questions
What's holding back self-driving cars as discussed in the episode George Hotz: Hacking the Simulation & Learning to Drive with Neural Nets | Lex Fridman Podcast #132 and the clip Autonomous Driving Insights?
What's holding back self-driving cars as discussed in the episode George Hotz: Hacking the Simulation & Learning to Drive with Neural Nets | Lex Fridman Podcast #132 and the clip Autonomous Driving Insights?