Skoči na glavni sadržaj

VSITE Workshop „Deep Learning - Basic Tool in Artificial Intelligence “

Workshop „Deep Learning - Basic Tool in Artificial Intelligence “

The workshop will cover basic ideas, approaches, techniques, and applications of Neural Networks (NN), Deep Learning (DL), and Artificial Intelligence (AI) and it is aimed at all interested in using these tools in their field of interest. It will cover the core techniques used today and in particular, it plans to introduce error backpropagation algorithm (EBP), single layer NNs and their extensions to multilayers learning structures dubbed DL. The course will combine interactive lectures, exercises and Python code demonstrations aiming at mastering the concepts and get acquainted with the tools which would later enable all the participants to use them in their applications and projects. The workshop will not be focused on specific applications but rather give a broad introduction to the exciting new ideas and approaches in AI. The program includes hands-on examples demonstrating practical aspects.

All activities will be both face-to-face and online with Microsoft Teams platform.

We are looking forward to seeing you participate in this workshop.

Program

Day 1. Tuesday, 10th May 2022

Morning session, 9 – 12 AM, Prof. Vojisav Kecman, Ph.D., M. Sc., Dipl.-Ing.

  • Basics of Machine Learning
  • Supervised vs Unsupervised Learning
  • Feed-Forward Neural Networks
  • Error Back Propagation
  • Bias and Variance in Neural Networks

Afternoon session, 3 – 6 PM, Prof. Tomasz Arodz,Ph.D.

  • Automated Differentiation (AD)
  • PyTorch example of Automated Differentiation
  • Problems in training Deep Networks and how to overcome them.
  • Convolutional Neural Networks (CNNs)
  • Residual Networks (ResNets)
  • Self-attention-based Networks (Transformers)

Day 2. Wednesday, 11th May 2022

Morning session, 9 – 12 AM

  Individual Exercise Session based on materials provided by Prof. Arodz

Afternoon session, 3 – 6 PM, Prof. Tomasz Arodz, Ph.D.

  • Building deep networks from modules in PyTorch
  • PyTorch example of Convolutional Deep Network for image recognition
  • PyTorch example of an Attention-based Deep Network for language tasks
  • TensorFlow as an alternative to PyTorch

Application and Registration

Required prerequisites are: basic knowledge of Python, a basic uderstanding of linear algebra and single variable calculus.

Workshop AI Fee is HRK 1 000 (EUR 133 )

Online application form click here

The deadline for applications is May, 89, 2022.

Cancellation Policy

Notification of cancellation must be submitted in writing no later than May, 6, 2022.

Please send any additional inquiries regarding the registration process to workshop@vsite.hr

College for Information Technologies, VSITE

Postal address: Klaićeva 7, 10000 Zagreb

e-mail: workshop@vsite.hr

TAGS

Klaićeva 7, 10000 Zagreb, tel. 01/3764200 fax. 01/3764264