« All Events

Practical deep learning

May 6 • 09:00 – May 8 • 12:00 CEST

Register here
Practical deep learning @ ENCCS.

General introduction

Deep learning is a subset of machine learning that focuses on training artificial neural networks with multiple layers to recognize patterns and to simulate the complex decision-making power of the human brain. The use of deep learning has seen a significant increase of popularity and applicability over the last decade. While it serves as a powerful tool for researchers across various domains, taking the first steps into the world of deep learning can be somewhat intimidating.

This three-day online workshop aims to provide beginners with a foundational understanding of deep learning concepts, workflows, network architectures, and applications.

On the first two days, a gentle introduction to deep learning is presented. Starting with explanation of the basic concepts, we dive into different steps of a deep learning workflow using Python, Tensorflow and Keras – preparation of training data, implementation of a basic neural network, monitoring & troubleshooting the training process, and visualizing results & model performance.

On the final day of the workshop, we conclude with demos of three representative applications. These will illustrate how deep learning is shaping modern technology across healthcare, image processing, and natural language understanding.

  • Deep learning is revolutionising drug discovery by accelerating the identification of potential drug candidates and reducing research costs. For this application case, we will start from a Transformer-based tool trained on scRNA-seq data, getting familiar with the resulting embeddings and then adapt it to a specific scenario through fine-tuning, identifying promising proteins and finding potential molecular candidates for fixing issues through techniques such as molecular simulations.
  • Computer vision enables machines to interpret and analyse visual data, with deep learning models excelling at image classification, object detection, and segmentation. In this session, we will emphasise CNN-based architectures for medical image classification, covering key models, their role in feature extraction and decision-making, as well as dataset preprocessing, transfer learning, and evaluation metrics.
  • Large language models (LLMs), such as ChatGPT, have transformed natural language processing (NLP) by enabling machines to understand, generate, and analyse human language. In this session, we will discuss the LLM parallelisation on high-performance computing systems and explore the acceleration of complex LLM models for vision tasks using HPC resources.

A detailed schedule will be added in the upcoming days.

Who is this webinar for?

This beginner-level workshop is designed for individuals interested in learning the fundamentals of deep learning and how it applies to fields such as drug discovery, computer vision, and large language models (LLMs). The target audience includes:

  • students and early career researchers in computer science, bioinformatics, materials science and engineering, or related fields
  • industry engineers in pharmaceuticals, healthcare, etc.
  • data scientists and software developers for deep learning-based applications

Prerequisites

Participants are expected to have the following knowledge:

  • basic Python programming skills and being familiar with standard Python packages (Numpy, Pandas, Matplotlib, etc.).
  • basic knowledge of classical (“shallow”) machine learning methods is beneficial but not mandatory (such methods are not covered during this workshop)
  • basic knowledge of data statistics and working with a Linux/Unix environment are beneficial

Key takeaways

By the end of this workshop, the participants will be able to:

  • understand the basics of deep learning (classification, regression, clustering, etc.) and its relationship with machine learning and artificial intelligence
  • prepare input data
  • design and train a deep neural network using Python, TensorFlow and Keras
  • measure the performance of the network and visualise the results
  • troubleshoot the learning process
  • understand overfitting, underfitting, and techniques like regularization
  • re-use existing network architectures with and without pre-trained weights
  • write well-structured Jupyter notebooks for deep learning workflows
  • get familiar with advanced topics like CNNs, RNNs, and transformers along with real-world applications of deep learning (e.g., image recognition, NLP)

More events & contact

Check out more upcoming events from ENCCS and our European network at https://enccs.se/events.

For questions regarding this workshop or general questions about ENNCS training events, please contact training@enccs.se

Schedules can change!

To ensure that everyone has the opportunity to participate, we kindly request that you let us know as soon as possible if you are unable to attend an event after registering.

Please send us an email at training@enccs.se to cancel your attendance.

We understand things can change, but repeated cancellations without notice may unfortunately result in your name being removed from future event registration lists.

Regulations

Due to EuroCC2 regulations, we CAN NOT ACCEPT generic or private email addresses. Please use your official university or company email address for registration.

This training is for users who live and work in the European Union or a country associated with Horizon 2020. You can read more about the countries associated with Horizon2020 HERE.

ENCCS

Related Events