Skoči na glavni sadržaj

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

Workshop „Deep Learning - Basic Tool in Artificial Intelligence “

Welcome to the home page of the 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 sessions, demonstrating practical aspects.

All activities will be online – on the Microsoft Teams platform.
We are looking forward to seeing you participate in this workshop.

Day 1. Tuesday, 23 March 2021

Morning session, 9 – 12 AM, Prof. Kecman
    Basics of Machine Learning
    Supervised vs Unsupervised Learning
    Feed-Forward Neural Networks
    Error Back Propagation
    Bias and Variance in Neural Networks

Afternoon session, 2 – 5 PM, Prof. Arodz
    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, 24 March 2021

Morning session, 9 – 12 AM, 
    Exercise Session

Afternoon session, 2 – 5 PM, Prof. Arodz
    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
 

Please consider that the required prerequisites are: at least basic knowledge of Python, a basic understanding of matrix algebra, and single variable calculus.

Workshop AI Fee is HRK 1 000 (EUR 133 )

Online application form click here
The deadline for applications is March, 22, 2021.

Cancellation Policy
Notification of cancellation must be submitted in writing no later than March, 19, 2021.
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
Oznake

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