Introduction to Deep Learning in TensorFlow

This is the repository for the Deep Dive: Introduction to Deep Learning in TensorFlow, organized by Cornell Data Science.
No prior knowledge in machine learning or Python is assumed, except for simple matrix algebra and basic understanding of coding.

The associated lecture recordings can be found here.

Installation

To download all course material, type the following into the command-line:

git clone https://github.com/CornellDataScience/Deep-Learning-Course.git

For those with native pip, use the following to install all dependencies:

pip install -r requirements.txt

All material is written in Python 3 (although most code is Python 2-compatible).
For detailed installation instructions on git, Python, and TensorFlow, see the installation section.

Tutorials

1. Linear Classifiers
2. Fully Connected Neural Networks
3. Convolutional Neural Networks
4. Recurrent Neural Networks

About

Authors: Yuji Akimoto (CS '19), Ryan Butler (CS '19)

Course material is inspired by the CS231n course at Stanford University and the tutorials by Hvass-Labs.
All material is distributed under the MIT License.