Deep Learning is an emerging topic in data analysis. Deep Networks are special kinds of neural networks that try to mimic biological neural networks in hardware or software. Though neural networks is a very old topic in computer science, in recent years surprising advances have been made in this area. This is evidenced by several awards in very diverse learning competitions including speech, handwriting recognition, speech translation, vision, and game playing. Some of these advances are due to better learning algorithms and/or very clever network architectures, others are simply due to much better, highly parallel hardware. More recently, companies like Google and Facebook have started making major investments in the area of deep learning, e.g. in 2014, Google acquired Deep Mind for approximately 500 million pounds; and Facebook founded a deep learning lab in Paris. In addition, some of the fascinating results of deep learning created big waves in the press, e.g. Google Inceptionism and Google Deep Dream.
In this seminar we will investigate what is behind deep learning. We will loook at fundamental techniques, network architectures, learning algorithms, frameworks, and applications.
The seminar will be classical in the sense that students are expected to give presentations. In addition, we expect students to prepare demos.
The seminar is fully booked, please do not try to register anymore. Notifications will be sent out mid September.
However: if you want to listen to talks, you are welcome to attend them as a guest.
Starting October 26, we will meet every Monday at 14:15 in E1 3, HS 003.
Students are expected to have successfully passed at least one core lecture.
The number of participants is limited to 20 people.
For registering you must send an email to Prof. Dittrich. Please briefly list previous courses/experiences in the area of data management, AI, ML, DB, systems, etc. Please only send plain text or pdf.