#transformer#neuralnetworks#gradientdescent
33K subscribers • 1 video on Hallway
Beginner. No background in the topic needed.
375K views4 years ago3 recommendations
AI and machine learningComputer scienceTransformers and LLMsNeural networks and deep learningMath for machine learning
Steve Seitz explains the fundamentals of large language models, covering conditional probabilities, neural networks, gradient descent, and backpropagation.
How do language models like chatGPT and Palm work? A short cartoon that explains transformers and the tech behind LLMs. Part 2: youtu.be/YDiSFS-yHwk - intro - autocomplete - search query completion - language modeling with probabilities - time series and graphs - text generation - conditional probabilities - trigrams - universal function approximation - neural networks - gradient descent - back propagation - network capacityWhat people say. Recommended as a clear, non-technical introduction to how LLMs and neural networks work without dumbing down the content.
sainezon Hacker News • Recommends
On “A Completely Non-Technical Explanation of Deep Learning”
peter_d_shermanon Hacker News • Recommends
On “Large Language Models from scratch (2022)”
runetechon Hacker News • Recommends
On “Ask HN: Can someone ELI5 Transformers and the “Attention is all we need” paper”
mistermannon Hacker News • Mentions
On “Globalization Is Dead and No One Is Listening”
mistermannon Hacker News • Mentions
On “The Starship or the Canoe: Where will our future adaptations be? (2017)”