Learning from videos and recommending movies with Deep Neural Networks - Ondřej Bíža
Deep Learning techniques have shown tremendous success in classification and detection of objects in images. Extending the current state-of-the-art models to the video domain is the next step in the long and winding road to machine perception. In this talk, we will show you how we design new 3d convolutional neural nets with attention for better action detection from video. We will demonstrate how our deep neural networks learn from hundreds of thousands of noisy YouTube videos and give you some insights into what the models learn through visualizations. We will also present an application of the trained models to movie recommendation which we develop in cooperation with Showmax and Recombee.
Speakers: Ondřej Bíža
Ondřej Bíža is a research scientist in ShowmaxLab, a joint laboratory between the Czech Technical University and Showmax, and an undergraduate student. His research focuses on training neural networks to understand video and sound. Moreover, Ondřej teaches Deep Learning in the Methods of Computational Intelligence graduate course at the Czech Technical University and advises on the research of Deep Recommender Systems in Recombee.
- 18:00 The talk
- 20:00 Networking
Machine Learning Meetups (MLMU) is an independent platform for people interested in Machine Learning, Information Retrieval, Natural Language Processing, Computer Vision, Pattern Recognition, Data Journalism, Artificial Intelligence, Agent Systems and all the related topics. MLMU is a regular community meeting usually consisting of a talk, a discussion and a subsequent networking allowing people to network, inspire each other and learn about exciting stuff. At the end of the year 2016, MLMU spread also to Brno and Bratislava. The beginning of 4th season brought MLMU Košice!