Giter VIP home page Giter VIP logo

neuralnetworks-zero-to-hero's Introduction

NeuralNetworks-Zero-To-Hero

Neural Networks: Zero to Hero is a course on deep learning fundamentals by the renowned AI researcher and educator Andrej Karpathy. This repository contains my personal lecture notes and exercise solutions for the course, which covers a wide range of topics such as neural networks, backpropagation, wavenet, GPT & more.

You can find the lecture notes and exercise here: https://anubhavmaity.github.io/NeuralNetworks-Zero-To-Hero/

If you want to play with lecture notes and exercise in Google Colab then head over to the Contents Section.

The youtube lectures of the course can be found here: https://karpathy.ai/zero-to-hero.html

Table of Contents

Course Overview

The “Neural Networks: Zero to Hero” course covers a range of deep learning topics, including:

- Neural Networks and Backward propogation
- Language Modeling
- MultiLayer Perceptron
- Activations & Gradients
- Batch normalizations
- Wavenet
- GPT
- And more!

Contents

This repository contains my personal notes and exercise solutions for each lecture in the course. The lecture notes provide a detailed summary of each lecture, including key concepts, equations, diagrams, and examples. The exercise solutions include code and written explanations, helping you to deepen your understanding of the material and apply it in practice.

Lecture 1: The spelled-out intro to neural networks and backpropagation: building micrograd

Style Colab Github
Lecture Note Open In Colab Open In GitHub
Exercise Open In Colab Open In GitHub

Lecture 2: The spelled-out intro to language modeling: building makemore

Style Colab Github
Lecture Note Open In Colab Open In GitHub
Exercise Open In Colab Open In GitHub

Lecture 3: Building makemore Part 2: MLP

Style Colab Github
Lecture Note Open In Colab Open In GitHub
Exercise Open In Colab Open In GitHub

Lecture 4: Building makemore Part 3: Activations & Gradients, BatchNorm

Style Colab Github
Lecture Note Open In Colab Open In GitHub
Exercise Open In Colab Open In GitHub

Lecture 5: Building makemore Part 4: Becoming a Backprop Ninja

Style Colab Github
Lecture Note & Exercise Open In Colab Open In GitHub

Lecture 6: Building makemore Part 5: Building a WaveNet

Style Colab Github
Lecture Note Open In Colab Open In GitHub
Exercise Open In Colab Open In GitHub

Usage

You can use this repository to review and reference the lecture notes, as well as to deepen your understanding of the concepts through the exercise solutions. You can also modify and build upon the code to suit your own needs.

If you use this repository in your project, please attribute it to me (Anubhav Maity) and include a link to the original repository:

Contributing

Contributions to this repository are welcome! If you notice any errors or have suggestions for improving the content, feel free to submit a pull request or open an issue.

The docs are generated from Jupyter Notebooks using nbdev. To make any changes in the doc, you can make the changes in the Jupyter Notebook and the Github Action will generate the docs from the notebook for you.

LICENSE

This repository is licensed under the Apache License 2.0. See the LICENSE file in the repo for details.

neuralnetworks-zero-to-hero's People

Contributors

anubhavmaity avatar

Stargazers

 avatar Suchit G avatar AHMED avatar Martin Milan avatar Deven Mistry avatar Karapet avatar

Watchers

James Cloos avatar  avatar  avatar

Forkers

deven367

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.