Interview
summary
Artificial intelligence shifts self-driving systems from handcoded rules developed over the last 20 years toward deep learning trained on large diverse datasets, claiming within the next five years data-driven models will handle unforeseen scenarios better than rule lists. Companies already test autonomous vehicles on streets using classical robotics stacks while teams collect driving logs and human demonstrations to train models. Udacity builds curricula to produce software engineers capable of deploying these ML systems.
AI-written summary · about
related talks
36mArtificial Intelligence: The Future of Software
21mFuture in Motion: Robotics, Self-Driving Cars, and Humanoids Shaping Tomorrow
31mDeep learning for self-driving vehicle technology
02mAI-defined vehicles and autonomy
52mPhysical AI: Crafting Resilient Systems with Emotional Intelligence
10mAI for automation, algorithms, and intelligent agents
29mThe Present & Future of AI and Games
48mMachine Takeover - Improving Your Game With Machine Learning & AI