Dec 28, 2022Felhasználói élmény — UX és interakció mellékspecializáció a BME-nAz Adattudomány és Mesterséges Intelligencia főspecializáció kiváló kiegészítője a BME VIK-en a UX és interakció mellékspecializáció. A mellékspecializáció a mesterséges intelligencia (AI) és a felhasználói élmény (UX) területén nyújt gyakorlat orientált képzést a hallgatóknak. A felhasználói élmény (User Experience, UX) megtervezése és megvalósítása magába foglalja egy termék létrehozásának és alkalmazásba…Deep Learning4 min readDeep Learning4 min read
Nov 10, 2022Adattudomány és Mesterséges Intelligencia MSc főspecializáció a BME-n“Elméleti és gyakorlati MI tudás az ipar igényeihez igazítva” — 2023 februártól a Méréstechnika és Információs Rendszerek Tanszék és Távközlési és Médiainformatikai Tanszék data science és machine learning szakértőivel közösen elindítjuk a BME VIK-en az Adattudomány és Mesterséges Intelligencia MSc főspecializációt. A specializációban az elméleti alapok és gyakorlati anyagok minél…Masters Degree5 min readMasters Degree5 min read
Apr 28, 2022PIA project’s achievement at NeurIPS AIDO6Author: Robert Moni, András Kalapos, András Béres, Bence Háromi, Dávid Bárdos, Tibor Áron Tóth, Bálint Gyires-Tóth In December 2021 our team competed with 5 different solutions at the 6th edition of the AI Driving Olympics (AIDO) which was part of the 35th conference on Neural Information Processing Systems (NeurIPS). …Self Driving Cars5 min readSelf Driving Cars5 min read
Mar 3, 2021Using Transfer Learning to solve the simulator-to-real problem in the Duckietown environmentAuthor: Zoltán Lőrincz Introduction Throughout the previous semesters, I used Imitation Learning to carry out lane following in the Duckietown¹ environment. The agents were trained in the Duckietown simulator using different Imitation Learning methods such as Behavioral Cloning², Dataset Aggregation³ (DAgger) and Generative Adversarial Imitation Learning⁴ (GAIL). …Deep Learning6 min readDeep Learning6 min read
Feb 26, 2021PIA project’s perseveranceAuthor: Robert Moni Sorry for the clickbait, but no, we aren’t the engineers that put together the Perseverance Mars rover, although we do possess the right amount of perseverance to achieve our goals. This blog post attempts to provide a summary of our latest research achievements under the aegis of…Deep Learning5 min readDeep Learning5 min read
Feb 25, 2021Deep Learning-based Semantic Segmentation in Simulation and Real-World for Autonomous Vehicles — part 2Author: Zsombor Tóth Part 1 of this blog post can be found here. Introduction Deep Learning is one of the most important techniques of autonomous vehicles nowadays. There are many components of a self-driving vehicle that can be realized with the help of deep neural networks (e.g. car and pedestrian detection…Neural Networks4 min readNeural Networks4 min read
Feb 25, 2021Apply semi-supervised learning for semantic segmentationAuthor: Gábor Lant One of the key strength of deep learning is that it can work with a large amount of data to train machine learning models. These models can be trained to find the underlying structure of the data. On the other hand, this also means that data is…Deep Learning4 min readDeep Learning4 min read
Feb 25, 2021Disjoint Datasets in Multi-task Learning with Deep Neural Networks for Autonomous DrivingAuthor: Tamás Illés Introduction In Machine Learning (ML), we typically care about optimizing for a particular metric, whether this is a score on a certain benchmark or a business Key Performance Indicator (KPI). In order to do this, we generally train a single model or an ensemble of models to perform…Deep Learning4 min readDeep Learning4 min read
Feb 25, 2021Supervised and Unsupervised Representation Learning for Reinforcement LearningAuthor: András Béres Introduction Recently the topic of self-driving cars has received great attention both from academia and the public. While Deep Learning can provide us tools for processing vast amounts of sensor data, Reinforcement Learning promises us the ability to take the right actions in complex interactive environments. …Deep Learning5 min readDeep Learning5 min read
Feb 25, 2021Lane following in the Duckietown environment under extreme conditionsAuthor: Péter Almási I set the goal to create a method for controlling vehicles to perform autonomous lane following using deep reinforcement learning. The agent is trained in a simulated environment without any real-world data and is tested in the real world. …Deep Learning6 min readDeep Learning6 min read
