#01视频
用短视频讲解 AI
每个视频讲一个概念，语言通俗易懂。每个视频都链接到我们免费课程中分步讲解的对应章节。
从这里开始 AI 101
- #01
#02Machine learning: how a computer draws its own dividing line
#03Neural networks: layers of tiny calculators passing signals on
#04How AI learns: guess, measure the error, nudge, repeat
#05Tokens: how AI chops your words into numbered pieces
#06Embeddings: why a puppy lands closer to a dog than to a pizza
最新
#031Momentum: how remembering past steps stops AI training zigzagging
#030Mini-batches: why AI learns faster from a random handful of data
#029Saddle points: where AI training looks stuck but has a way down
#028Local minima: why AI training can settle for second best
#027Condition number: why a stretched valley makes AI training crawl
#026Learning rate: the step size with a ceiling you can calculate
#025Gradient descent: how AI finds its way downhill in small steps
#024Gradient: the arrow that points uphill, and why AI walks the other way
#023Chain rule: how AI traces the effect of every layer
#022Derivative: how much the result moves when you nudge one input
#021Grid search: why you cannot train an AI by trying every setting
#020Robust loss: stop one wild reading from wrecking your forecast
#019Heavy tails: when rare, huge errors break the usual average
#018Mean squared error: the hidden bet behind squaring your mistakes
#017The LogSumExp trick: one subtraction that stops AI math overflowing
#016Rounding error: why adding the same numbers can give two answers
#015Floating-point numbers: why your computer cannot hold every number
#014Negative log-likelihood: turning a fragile product into a calm sum
#013Maximum likelihood: the answer that makes your data least surprising
#012Bayes' rule: reasoning backwards from a clue to its most likely cause
#011Chain rule of probability: how AI scores a sentence word by word
#010Loss landscape: training an AI means finding the bottom of a valley
#009Loss function: the scoring rule that decides which answer wins
#008Feature engineering: the human choice that can beat the algorithm
按课程章节
- 1从零实现感知机：一个神经元到底计算什么10 个视频
- 2损失函数从何而来：是似然，不是惯例12 个视频
- 3下坡：Gradient Descent，以及所有人都跳过的两个步骤12 个视频
- 4分类、交叉熵，以及如何不被自己骗倒
- 5从零实现 Backpropagation：先造引擎，再搭网络1 个视频
- 6让它能训练，也让它能泛化
- 7构建一个 BPE Tokenizer：模型为什么数不清 R1 个视频
- 8Next-token 预测：embedding，以及困惑度到底意味着什么1 个视频
- 9从平均值推导 Attention 与 transformer block
- 10预训练 LLM：数据、算力、Scaling Laws 与成本
- 11从基础模型到助手：SFT、RLHF、DPO 与 GRPO
- 12Chain of Thought、RLVR 与 Test-Time Compute：一次实测
- 13让推理更便宜：KV cache、批处理与量化
- 14你的第一次生产级 LLM 调用：流式传输、重试与超时
- 15用测量理解 Prompt Engineering：什么会改变输出
- 16把 context window、token 和账单算清楚
- 17温度、top-p，以及你并不拥有的确定性
- 18Tool Calling 与结构化输出：守得住的契约
- 19生产环境中的 RAG：chunking、检索与诚实引用
- 20Fine-Tune、检索还是 Prompt？决定因素是经济账
- 21多模态定价：图像、音频和视频到底按什么收费
- 22AI agent 是什么：五种经典类型与两种相互竞争的定义
- 23构建 agent harness：循环与五种退出方式
- 24Context Engineering：为什么你的 agent 到第 40 轮会变笨
- 25Multi-Agent 编排：五种模式，以及何时单 agent 胜出
- 26对照规范解释 MCP：服务器到底是什么
- 27发布一个 MCP Server：TypeScript 与 Python 实测对比
- 28Agent Skills 与 SKILL.md：实测渐进式披露
- 29LLM 评估：从公开 benchmark 到你的黄金集
- 30Prompt injection 与致命三角：保护真实 agent