Online course: Diving into deep learning - theory and applications with PyTorch
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. 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.
Application deadline: 31 October 2024
Date: 07 - 08 November 2024
General information
- Date: 07 - 08 November 2024
- Time: 9:00-17:00 CET
- Location: Online
- Fees:
- Academic: 200 CHF
- For-profit: 1000 CHF
Description
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.
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
- 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).