atcold/nyu-dlsp20

★ 6,806Jupyter NotebookAudience · researcherComplexity · 2/5Setup · moderate

Mindmap

mindmap
  root((NYU-DLSP20))
    What it does
      University course archive
      Lecture videos linked
      14 language translations
    Tech Stack
      Python
      PyTorch
      Jupyter Notebook
    Use Cases
      Self-paced study
      Run code exercises
      Follow lecture topics
    Audience
      Students
      AI beginners
      Self-learners

mindmap root((NYU-DLSP20)) What it does University course archive Lecture videos linked 14 language translations Tech Stack Python PyTorch Jupyter Notebook Use Cases Self-paced study Run code exercises Follow lecture topics Audience Students AI beginners Self-learners

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Work through NYU's Deep Learning curriculum at your own pace using interactive Jupyter Notebook exercises

USE CASE 2

Experiment with neural network code from a university course directly on your own machine

USE CASE 3

Study deep learning concepts alongside the linked lecture videos from a structured academic syllabus

USE CASE 4

Access translated course materials in over fourteen languages including Mandarin, Spanish, and French

Tech stack

PythonPyTorchJupyter NotebookMiniconda

Getting it running

Difficulty · moderate Time to first run · 30min

Requires installing Miniconda and creating a conda environment before Jupyter notebooks will run.

In plain English

This repository contains the course materials for NYU's Deep Learning course from Spring 2020, taught by Alfredo Canziani. The course covers how to build and train neural networks, the branch of artificial intelligence that powers most modern AI applications. All lecture videos and written notes are available on the companion website at atcold.github.io/NYU-DLSP20. The repository itself holds interactive coding exercises in the form of Jupyter Notebooks, which are documents that mix written explanations with runnable code. Each notebook corresponds to a lecture topic, and students can follow along by running the code on their own machine and experimenting with it directly. The exercises use PyTorch, a popular Python library for building neural networks. To run the notebooks locally, you need to install Miniconda (a lightweight Python environment manager), clone this repository, create the provided conda environment, and then launch Jupyter from the terminal. Detailed setup instructions for Mac, Linux, and Windows are included in the README. The course materials have been translated into at least fourteen languages by community contributors, including Mandarin, Spanish, French, Japanese, Arabic, Russian, and Portuguese, among others. Each translation lives in its own folder within the repository. This is a standalone educational resource, not an active software project. It exists as an archive of a university course that anyone can work through at their own pace.

Copy-paste prompts

Prompt 1

I'm working through the NYU-DLSP20 course. Walk me through the notebook for week 3 and explain each code cell in plain English so I can follow along.

Prompt 2

Help me set up the NYU-DLSP20 Miniconda environment on my Mac so I can run the PyTorch notebooks without any import errors.

Prompt 3

Using the NYU Deep Learning 2020 exercises as a reference, write me a simple PyTorch neural network that classifies handwritten digits and explain each layer.

Prompt 4

I want to understand backpropagation. Point me to the relevant NYU-DLSP20 notebook and walk me through the code that demonstrates it step by step.

Open on GitHub → Explain another repo

← atcold on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.