Interferometric Synthetic Aperture Radar (InSAR) technology uses satellite radar to detect surface deformation patterns and monitor earthquake impacts on buildings. While vital for emergency response planning, extracting multi-class building damage classifications from InSAR data faces challenges: overlapping damage signatures with environmental noise, computational complexity in multi-class scenarios, and the need for rapid regional-scale processing. Our novel multi-class variational causal Bayesian inference framework with quadratic variational bounds provides rigorous approximations while ensuring efficiency. By integrating InSAR observations with USGS ground failure models and building fragility functions, our approach separates building damage signals while maintaining computational efficiency through strategic pruning. Evaluation across five major earthquakes (Haiti 2021, Puerto Rico 2020, Zagreb 2020, Italy 2016, Ridgecrest 2019) shows improved damage classification accuracy (AUC: 0.94-0.96), achieving up to 35.7% improvement over existing methods. Our approach maintains high accuracy (AUC > 0.93) across all damage categories while reducing computational overhead by over 40% without requiring extensive ground truth data.

The Rimac Group describes Verne--its new autonomous ride-hailing service--as its "next impossible thing." First, founder Mate Rimac established his eponymous electric hypercar company in Croatia, a country with no history of carmaking. Porsche, Hyundai and Softbank all took stakes. Rimac Technology now supplies electric drivetrains to Porsche, BMW and Aston Martin, among many others, and it is developing advanced energy storage tech, too. And now there's Verne, Mate's autonomous ride-hailing service launched today in Zagreb, the Croatian capital.

On his office desk, Aleksandar Gavrilovic keeps two figurines: Vladimir Lenin, the Russian revolutionary, and Josip Broz Tito, the former communist leader of Yugoslavia. Gavrilovic is the founder of the video game company Gamechuck. Based out of a tiny office crammed with computers in Zagreb, the capital of Croatia, the company is organized around equality: Each worker earns the same salary and shares the profits of the games they create. All decisions are reached through anonymous voting on Discord: The 17-person collective recently voted to shorten workdays from eight hours to six. "We wanted to show that you don't actually have to work like everyone else to be successful," said Gavrilovic. Gavrilovic's company is an outlier in the gaming industry, known for its grueling hours, high turnover rates, and worker discontent.

Professional development: As the gaming industry is constantly evolving and growing, we can promise you will, too! We will ensure you have a structured and smooth onboarding process with scheduled feedback times and both a mentor and a buddy by your side. To make sure you and your team are up to date with the latest trends, we allocate a team budget for education. Financial benefits: On top of a competitive salary, we offer additional financial benefits based on annual success, such as a Christmas bonus, Easter bonus, summer bonus, 13th salary, as well as referral bonuses and fully covered transportation expenses. Work-life balance: We are deeply dedicated to our work, but also understand the importance of switching off and recharging.

With over 270 million downloads globally, Photomath is the #1 app in the world to learn math and one of the most popular educational apps of all time. Powered by advanced machine learning technology, the app instantly scans, accurately solves, and intuitively explains printed and handwritten math problems to users through step-by-step explanations. Since its launch in 2014, our award-winning app has topped App Store & Google Play Store education charts and Apple has recently declared it the application of the day. Today, we employ more than 150 people and have offices in Zagreb and San Mateo, California. We are constantly expanding what Photomath can do and the types and quality of our content - we have so much more ahead of us and we need your help to get there.

He is working on improving the performance and safety of our machine learning models. Originally from Zagreb, Croatia, Vilim studied electrical engineering and computer science for his bachelor's degree. He increasingly became intrigued with neuroscience, which became the focus of his Master's degree at LMU in Munich. Vilim stayed on in Munich to obtain his PhD at the Max Planck Institute of Neurobiology, where he investigated neural processing for motor control with whole-brain imaging. Machine learning has always been a part of Vilim's work and studies, and he is excited to completely focus on it for his new role.

Typically when we write about food making robots, they fall into either one of two categories: Smaller countertop devices meant for the home, or larger, more industrial robots meant for restaurant kitchens. But a restaurant called Bots&Pots in Zagreb, Croatia, is combining those two ideas and using a number of GammaChef cooking robots to make meals for its customers. GammaChef, also based in Croatia (and also a former Smart Kitchen Summit Startup Showcase finalist), makes the eponymous robot capable of creating one-pot dishes such as stews, risottos and pastas. The device stores ingredients, dispenses them into the pot, and stirs the food as it cooks. According to Total Croatia News, customers at Bots&Pots choose their meal via touchscreen at one of five GammaChefs inside the restaurant and they'll be able to see their meal prepared.

CRTA is a regional center of excellence for robotic technology within the faculty of mechanical engineering and naval architecture at the university of zagreb, croatia. 'the visual representation of the concepts contained in the definition of the word line is a symbolic representation of the process of growth i.e. the trainings provided to the center's beneficiaries.

Proving that Central and Eastern Europe remains a powerhouse of hardware engineering matched with software, Gideon Brothers (GB), a Zagreb, Croatia-based robotics and AI startup, has raised a $31 million Series A round led by Koch Disruptive Technologies (KDT), the venture and growth arm of Koch Industries Inc., with participation from DB Schenker, Prologis Ventures and Rite-Hite. The round also includes participation from several of Gideon Brothers' existing backers: Taavet Hinrikus (co-founder of TransferWise), Pentland Ventures, Peaksjah, HCVC (Hardware Club), Ivan Topčić, Nenad Bakić and Luca Ascani. The investment will be used to accelerate the development and commercialization of GB's AI and 3D vision-based "autonomous mobile robots" or "AMRs". These perform simple tasks such as transporting, picking up and dropping off products in order to free up humans to perform more valuable tasks. The company will also expand its operations in the EU and U.S. by opening offices in Munich, Germany and Boston, Massachusetts, respectively.

Recently, we visited The Data Science Economy conference in Zagreb. More than 30 speakers covered a lot of real-life use cases, best practices, and future trends in the field of Data Science. We also participated in "Deep Dive into Deep Learning„ workshop held by Leonardo De Marchi, the Lead Data Scientist in Badoo (Badoo is the largest dating site with over 360 million users). As the Deep Learning is part of our daily work and also the main trend in AI, we decided to share with you some of the insights we learned at this workshop and help you to start your own first deep learning project. We will go through some of the basic Deep Learning concepts with Keras.