Workshop: (Deep) Learn Neural Networks with PyTorch

Location: Rutherford, 4th flr.

Duration: 9:00am - 4:00pm

Day of week: Friday

Level: Beginner

Key Takeaways

  • Build a neural network, learn PyTorch, use your GPU easily to compute faster.

Prerequisites

Attendees need to have the following things installed on their laptops:

  • Python 3.7 if you have an Nvidia GPU:
    Cuda https://developer.nvidia.com/cuda-downloads
    Cudnn https://developer.nvidia.com/cudnn
  • If you don't have this, we highly recommend the hosted solution. 

We will send out a detailed e-mail with instructions to run ‘pip install -r requirements.txt‘ to install PyTorch 2 weeks before the conference.

This workshop will teach you PyTorch and building neural networks with it. 
It will provide you with all the necessary knowledge to get started with crunching vast amounts of data and generating rules from them.
You will learn the following:
  • Build and train a Perceptron in numpy
  • Move the code to the GPU using PyTorch
  • Extend the neural network for more complex time-series forecasting
  • Introduction to NLP
  • TCN vs. RNN
This workshop aims at programmers comfortable with Python who want to expand their skills towards neural networks. It is recommended to be familiar with the basics of machine learning (but not mandatory). E.g. being familiar with train, validation, test splits and scaling would be perfect. 
It is not required that you have dealt with neural networks before.
You won’t need to setup your computer for this workshop either. 
We will take care of providing you an adequately setup cloud instance.
For those of you who prefer programming locally and having a computer with an NVIDIA GPU and Linux, instructions for preparing the computer will be sent out, too.

Speaker: Patrick Mölk

Software Engineer @Nooxit

Patrick is Head of Engineering at Nooxit. He recently finished his master’s degree in Computer and Communications Systems Engineering with a thesis on machine learning with an emphasis on natural language processing. He formerly worked as a working student and as an electrical engineer in the industry developing software for programmable logic controllers.   
He likes all things regarding automation and generally making life easier through software.

Speaker: Jendrik Jördening

Data Scientist @Nooxit

Jendrik is Head of Data Science at a stealth startup. He formerly worked at Aurubis and Akka Germany on Data Science and Deep Learning in the field of industry 4.0 and autonomous machines.

At the same time he took part in the Udacity Self-Driving Car Nanodegree, participating with a group of other Udacity student in the Self-Racing Cars event at the Thunderhill race-track in California.

Find Jendrik Jördening at

Tracks

The all-new QCon app!

Available on iOS and Android

The new QCon app helps you make the most of your conference experience. Easily browse and follow the conference schedule, star the talks you want to attend, and keep tabs on your personal itinerary. Download the app now for free on iOS and Android.