BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:[Online] Practical Deep Learning @ ENCCS
DTSTART:20250506T070000Z
DTEND:20250508T100000Z
DTSTAMP:20260720T184500Z
UID:indico-event-1602@events.prace-ri.eu
DESCRIPTION:General introduction\n\nDeep learning is a subset of machine l
 earning that focuses on training artificial neural networks with multiple 
 layers to recognize patterns and to simulate the complex decision-making p
 ower of the human brain. The use of deep learning has seen a significant i
 ncrease of popularity and applicability over the last decade. While it ser
 ves as a powerful tool for researchers across various domains\, taking the
  first steps into the world of deep learning can be somewhat intimidating.
 \n\nThis workshop aims to provide beginners with a foundational understand
 ing of deep learning concepts\, network architectures\, and applications.\
 n\nFor the general introduction to deep learning\, we start with explainin
 g the basic concepts of neural networks\, and then go through different st
 eps of a deep learning workflow from the preparation of training data\, th
 e implementation of a basic deep learning model with Keras using Python\, 
 the detailed procedures to monitor and troubleshoot training process\, and
  the implementation of different layer types (*i.e.*\, convolutional layer
 s).\n\nIn addition\, we have three representative examples to illustrate h
 ow deep learning is shaping modern technology across healthcare\, image pr
 ocessing\, and natural language understanding.\n- 1) Deep learning is revo
 lutionizing 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\, ge
 tting familiar with resulting-embeddings and then adapt it to a specific s
 cenario through fine-tuning\, identifying promising proteins and finding p
 otential molecular candidates for fixing issues through techniques such as
  molecular simulations.\n- 2) Computer vision enables machines to interpre
 t and analyze visual data\, with deep learning models excelling at image c
 lassification\, object detection\, and segmentation. In this session\, we 
 will emphasize 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 m
 etrics.\n- 3) Large language models (LLMs)\, such as ChatGPT\, have transf
 ormed natural language processing (NLP) by enabling machines to understand
 \, generate\, and analyze human language. In this session\, we will discus
 s the LLMs parallelization on high-performance computing systems and explo
 re the acceleration of complex LLM models for vision tasks using HPC resou
 rces.\n\nWho is this workshop for\n\nThis beginner-level workshop is desig
 ned for individuals interested in learning the fundamentals of deep learni
 ng and how it applies to fields such as drug discovery\, computer vision\,
  and large language models (LLMs). The target audience includes:\n- studen
 ts and early career researchers in computer science\, bioinformatics\, mat
 erials science and engineering\, or related fields\n- industry engineers i
 n pharmaceuticals\, healthcare\, *etc.*\n- data scientists and software de
 velopers for deep learning-based applications\n\nPrerequisites\n\nParticip
 ants are expected to have the following knowledge:\n- basic Python program
 ming skills and being familiar with standard Python packages (Numpy\, Pand
 as\, Matplotlib\, *etc.*).\n- basic knowledge of classical ("shallow") mac
 hine learning methods is beneficial but not mandatory (such methods are no
 t covered during this workshop)\n- basic knowledge of data statistics and 
 working with a Linux/Unix environment are beneficial\n\nKey takeaways\n\nB
 y the end of this workshop\, the participants will be able to:\n- understa
 nd the basics of deep learning (classification\, regression\, clustering\,
  *etc.*)\n- define deep learning and its relationship with machine learnin
 g and artificial intelligence\n- recognize real-world applications of deep
  learning (e.g.\, image recognition\, NLP)\n- write well-structured Jupyte
 r notebooks for deep learning workflows\n- prepare input data and use Pyth
 on and TensorFlow/Keras to create a basic neural network\n- use TensorFlow
  and Keras for practical model development\n- understand overfitting\, und
 erfitting\, and techniques like regularization\n- implement a basic classi
 fication task\n- get familiar with advanced topics like CNNs\, RNNs\, and 
 transformers\n\nMore events & contact\n\nCheck out more upcoming events fr
 om ENCCS and our European network at https://enccs.se/events.\n\nFor ques
 tions regarding this workshop or general questions about ENNCS training ev
 ents\, please contact training@enccs.se\n\nSchedules can change!\n\nTo en
 sure 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 ev
 ent after registering.\n\nPlease send us an email at training@enccs.se t
 o cancel your attendance.\n\nWe understand things can change\, but repeat
 ed cancellations without notice may unfortunately result in your name bein
 g removed from future event registration lists.\n\n\nRegulations\n\nDue to
  EuroCC2 regulations\, we CAN NOT ACCEPT generic or private email addres
 ses. Please use your official university or company email address for regi
 stration.\n\nThis training is for users who live and work in the European 
 Union or a country associated with Horizon 2020. You can read more about t
 he countries associated with Horizon2020 HERE.\n\n \n\nhttps://events.pr
 ace-ri.eu/event/1602/
LOCATION:Online
URL:https://events.prace-ri.eu/event/1602/
END:VEVENT
END:VCALENDAR