Advanced Deep Learning & Tensor Tutorial

Advanced Deep Learning and Tensor Tutorial. RSVP here!

Pre-requirements:

Basic knowledge of deep learning (convolutions, MLP)

Knowledge of Python

Speakers:

• Jean Kossaifi
• Adrian Bulat

Schedule:

• Deep learning refresher — how to train your deep nets (1:00 - 1:30)
• Tensor methods Quickstart (1:30 - 2:00)
• Short break (2:00 - 2:10)
• Combining tensor methods and deep learning (2:10 - 3:00)
• Short break (3:00 - 3:10)
• Ultimate compression with (binary) quantisation of deep neural networks (3:10 - 3:40)
• Break + setup (3:40 - 4:00)
• Hands-on session + Q&A: (4:00 - 5:00)
  • training a neural network for image classification
  • Adding in tensor decomposition
  • Binarizing/Quantization the network

Hardware and Software Preparation:

You will need a laptop to get the most of the session, with Python (3.7 or higher) installed, along with PyTorch and TensorLy.

You also need to have the jupyter notebook installed.

Installation instructions

If you are new to Python or simply want a pain-free experience, I recommend you install the Anaconda distribution. It comes with all you need shipped-in and ready to use!

Once you have anaconda installed, you want to get either the Jupyter Lab, or the Jupyter Notebook. Typically, you can simply run:

conda install jupyterlab

For PyTorch, simply follow the instructions. With conda, it should be something like:

conda install pytorch torchvision -c pytorch

Finally, to install TensorLy to get the latest version, you can clone the Github repository. In the command line, run:

git clone https://github.com/tensorly/tensorly

cd tensorly

pip install -e .

Or, if you have an issue during installation, you can also use conda:

conda install -c tensorly tensorly

Download Tutorial Slides: Deep Learning, Tensor Methods