Hello world!
Welcome to WordPress. This is your first post. Edit or delete it, then start writing!
Segmentation of the Guatemala dataset
Introduction
Read the abstract and introduction at the beginning here about the dataset: * https://science.sciencemag.org/content/361/6409/eaau0137
What is this project about?
- We are collaborating with team of archeologists to process a Guatemala dataset with DL methods
- The task is very complex, You will be assigned a small subset of the problems to test, implement and evaluate.
- Selecting the most suitable tile for segmentation.The dataset contains multiple tiles with size (approx 17100 x 9800 pixels), that represents different transforms of the lidar source data
- Expected output: Multiple models, that perform well on the selected dataset for detection and segmentation.
SOA – Image classification
| Convolutional Neural Network Predictions |
|---|
  |
  |
:   |
Tools and technologies
- Python (pytorch, numpy, open cv…), Matlab (computer vision and deep learning toolboxes)
- QGIS
Literature
About the methods used:
- https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/
- https://blog.athelas.com/a-brief-history-of-cnns-in-image-segmentation-from-r-cnn-to-mask-r-cnn-34ea83205de4
- https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html
Contact information
- miroslav.jascur@tuke.sk
- marek.bundzel@tuke.sk
CIT Team Wins AI Guardians Competition
On June 18th, a team of PhD students at our lab (Andrij David, Ivan Čík, Lukáš Hruška, Fouzia Adjailia) won Microsoft\’s AI Guardians competition.
The next AI Guardians competition challenges students, researchers, and professors from universities across Europe to solve the global education problem using Artificial Intelligence. Due to safety concerns, this year\’s edition took place online via a Teams group call. The competition resulted in the implementation of creative solutions for students, researchers, and teachers in the field of education based on AI technology.
The idea of our team (Eduka) focused on education. We provide educators state-of-the-art technology to improve their teaching. This tool helps instructors understand how to engage their pupils. Hence by using the latest scientific advancements, we enhance education. Therefore we help every student to reach their highest potential.
All over Europe, only 6 promising teams made it for the final round. We went head to head as each of these 6 finalist teams tried to sell their idea to Microsoft\’s panel of specialists. What ensued was an impressive display of competitive zeal, as each group was well-prepared to make a stand in the Shark Tank Pitch. All these teams delivered highly powerful presentations, and everyone did not shy away from answering some of the challenging questions from the judges. But in the end, after a challenging battle, our team won this year\’s edition.
Gradient Based Optimization Methods
Our newest PhD student, Andrinandrasana David Rasamoelina presented his research in a seminar titled \”Recent Advances in Gradient Based Optimization Method for Deep Neural Network\”.
He gave an introduction to gradient-based optimization for deep neural networks, the history and problem caused by selected optimization algorithms which led to the elaboration of the recent state-of-the-art methods. He also provided a quick overview on the convergence of Deep Neural Network and which optimization algorithm to use for a specific problem.
Explainable AI
As part of the Slovak Artificial Intelligence Meetup, Patrik Sabol, MSc. gave a talk with the title \”Explainable Classifier Supporting Decision-making for Colorectal Cancer Diagnosis from Histopathological Images\”.
He presented the results of his current research regarding an application of semantically explainable classifier, Cumulative Fuzzy Class Membership Criterion (CFCMC), in the medical domain, specifically for colorectal cancer detection from histopathological images. The classifier, in contrast with commonly used classifiers for image classification, is able to provide additional information about its classification results in a human-friendly form. The proposed supporting system is currently being tested in clinical trials.
New GPU Server
The newest addition to our lab equipment is a new GPU server containing two GPUs: a Gigabyte RTX 2070 SUPER, and a Kingston HzperX Predator RGB. The engine has 2560 NVIDIA CUDA cores.
The GPU server will be used by PhD, graduate and undergraduate students to help them in their work and research.
Renovating our Aquarium
In the past weeks we\’ve been busy renovating and beautifying the aquarium in our lab.
Improving the Lab
As part of improving the lab, members refilled all bean bags to give our students a more comfortable alternative to sitting in chairs during long classes.
Quo Vadis AI in Slovakia?
Prof. Peter Sinčák gave a talk on AI research and application in Slovakia, sharing his views on the domain\’s present and future. You can watch the entire presentation in Slovak below:
Business Trip to China
Prof. Sincak has been on a business trip in China. The main purpose was to visit Yunnan University, where he signed an agreement about opening a Slovak-Chinese Center for Artificial Intelligence. After that he attended IWACIII conference in Chendu, China, where he gave a plenary talk about Digital Intelligence for Autonomous Social Robotics. Later, he visited Chengdu University of Electronic Technology, where he discussed actual trends in Artificial Intelligence. At the end of his business trip, he visited Dr. Xia in Huawei and had a talk with him about ATLAS AI COMPUTERS and has also visited UBTECH company that deals with the integration of AI and robotics.
1 2