Neural Networks: Zero to Hero

karpathy.ai
On the map Visit site

A free video series by Andrej Karpathy covering neural networks from scratch — backpropagation, makemore, GPT, and more.

Description

Разбирает micrograd и backpropagation (2ч25м), затем языковое моделирование в серии makemore: биграммная модель, MLP, батч-нормализация, и далее до трансформера. Автор объясняет, почему языковые модели — удобная точка входа в глубокое обучение.

Specs

Type Course
SectionLearning
Pricing free
Platform Web only
Systems web
Who forТем, кто уверенно пишет на Python и помнит базовую математику (производные, нормальное распределение).
Site languageen
VendorAndrej Karpathy

Found in sources

curated github-lists telegram

Similar in «Learning»

rasbt/LLMs-from-scratch
пошаговый учебник по созданию языковой модели уровня GPT
Machine Learning for Beginners
(⭐36k) <br>
microsoft/AI-For-Beginners
12 Weeks, 24 Lessons, AI for All!
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
karpathy/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
karpathy/nanochat
The best ChatGPT that $100 can buy.

Submit a site to the catalog

Just send the link — we will work out the rest.

We will review what you send and add it to the catalog if it fits.

Not sure how to implement it? We can help

Tell us about your task — we will pick the tools and suggest where to start.

0 / 5000
Verification code

Fields marked with an asterisk are required. Your data is used only to reply.