Introduction to Deep Learning with Keras for R

Lecturers

Daniel Falbel, Rstudio

Certificate Confirmation of participation
Target audience

Novice and advanced R users from all professional groups.

Costs
  • CHF 600.- for members of UZH/ETH and associated institutes
  • CHF 800.- for alumni of UZH/ETH, members of other universities, the public sector and non-profit organizations
  • CHF 1200.- for companies
Persons without current employment can register for the UZH/ETH fee upon request.
Course language English
Course description

The course offers an introduction to deep learning using the Keras library and it's R interface. It will cover the basic building blocks of modern deep learning like convolutional neural networks for image classification and recurrent neural networks for text data. You will also learn how to use pre-trained models with Keras to boost model performance when large datasets are not available and how to use Keras preprocessing machinery to improve your workflow.

Program:

  • What's Deep Learning and what's Keras?
  • Building your first Keras model:
    • Layers
    • Optimisers and loss functions
    • Fitting your model
  • Convolutional Neural Networks
    • Simple CNN
    • Image preprocessing and data augmentation
    • Using pre-trained models
  • Recurrent Neural Networks
    • Simple RNN
    • Text data preprocessing
    • Using pre-trained models
    • Seq2seq models
Dates

October 8-9, 2020
[canceled]

  After registering you will receive a short automatic confirmation by email. If you received this email you are successfully and bindingly registered for the course. For administrative reasons the written invoice won't be sent out until about two weeks before the course.