Overview

This course aims to give the participants some practical knowledge of deep learning models in life sciences.

With the rise of new technologies, the volume of omics data in biology and medicine has grown exponentially recently. A major issue is to mine useful predictive knowledge from these data. Machine learning (ML) is a discipline in which computer algorithms perform automated learning by using data to assist humans in dealing with a large volume of multidimensional data, and deep learning is one of these methods. Deep learning is based on artificial neural networks inspired by the structure and function of the human brain. It has been widely applied in computer vision, natural language processing, computational biology, etc.

This course will not make the participant an absolute expert in the complex and dynamic world of Deep-Learning. Still, it will aim to “break the ice” through the explaination and implementation of simple yet concrete, deep-learning models using the PyTorch library. Participants will be introduced to the basic building blocks of deep-learning models and how the main parameters are tuned and monitored to ensure the training of large models.

Audience

This course is aimed at PhD students, post-docs and researchers in life sciences who already know about Machine Learning and would like to discover and start practising Deep Learning with PyTorch.

Learning outcomes

At the end of the course, the participants will be able to:

Create simple deep-learning models
Identify deep learning parameters
Train, and evaluate a deep-learning auto-encoder model
Adapt a pre-existing deep-learning model to a new task using fine-tuning

Prerequisites

Knowledge / competencies required

Prior knowledge of ML concepts and methods is required.
A good fluency with the Python programming language, including working knowledge of common data analysis libraries such as numpy, panda, matplotlib or scikit-learn.
Familiarity with different omics data technologies (highly recommended).

Technical

The needed libraries are indicated in the dedicated page on the GitHub repo.

Application

This course is now full with a long wating list.

The registration fees for academics are 200 CHF and 1000 CHF for for-profit companies.

While participants may be registered on a first come, first served basis, exceptions may be made to ensure diversity and equity, which may increase the time before your registration is confirmed.

You will be informed by email of your registration confirmation. Upon reception of the confirmation email, participants will be asked to confirm attendance by paying the fees within 5 days.

Applications close on 10/10/2024 or as soon as the course is full. Deadline for free-of-charge cancellation is set to 25/10/2024. Cancellation after this date will not be reimbursed. Please note that participation in SIB courses is subject to our general conditions.

Venue and Time

This course will be streamed.

The course will start at 9:00 and end around 17:00.

Precise information will be provided to the participants in due time.

Additional information

Coordination: Grégoire Rossier

We will recommend 0.5 ECTS credits for this course (given a passed exam at the end of the course).

You are welcome to register to the SIB courses mailing list to be informed of all future courses and workshops, as well as all important deadlines using the form here.

Please note that participation in SIB courses is subject to our general conditions.

SIB abides by the ELIXIR Code of Conduct. Participants of SIB courses are also required to abide by the same code.

For more information, please contact training@sib.swiss.

Diving into deep learning - theory and applications with PyTorch