Unlocking the power of AI: A fundamentally different approach to building intelligent systems
summary
Claims a high-level Inkling language plus an AI engine and cloud service that hide low-level network design, using a TensorFlow backend for algorithms. Demonstrations include a Breakout/cart-pole/lunar-lander pipeline, synthetic and simulated training sources, and composable skills with concept curricula. Reported outcome: staged teaching and behavior composition reaches useful policies in under 10,000 episodes and exposes intermediate activations for debugging and reuse.
AI-written summary · about
chapters (10)
- 0:00Banzai and AI programming
- 3:11Existing AI programming approaches
- 4:58Machine teaching concept
- 7:08Machine teaching core ideas
- 8:35Banzai’s reinforcement learning demo
- 12:37Multi-concept learning with MNIST
- 15:06Behavioral learning in Lunar Lander
- 17:13Explainability and reusable AI skills
- 18:38Industrial AI applications and plans
- 19:20Q&A
related talks
14mFull-Stack AI Engineering from AI-Native Coding to Knowledge, Models, Infrastructure & OSS
47mEmbedding AI: Don’t Burn Your Fingers in the Heat of the AI revolution
33mThe Dawn Of Universal Creativity
56mCan I do AI?
45mBringing the Power of AI to Your Application
46mFullstack AI: The Building Blocks for Production Ready AI-Powered Software
42mAI First Learning
22mSpeaking the Same Language: Let AI (Finally) Understand You