Vergangene Events

Deep Learning in Action #3

Dieses Meetup liegt in der Vergangenheit

375 Personen haben teilgenommen

Details

Deep Learning in Action Third Edition

(By the ACM Student Chapter (http://munichacm.de))

Check out our official Event Website (http://munichacm.de/deeplearning/).

You can find our current schedule (http://munichacm.de/deeplearning/schedule/) here!

It's time for the third edition of our Deep Learning in Action and this time we are going to really rock the show! Our confirmed line-up includes a human and a humanoid rockstar speaker: Prof. Dr. Jürgen Schmidhuber, Winner of the IEEE Neural Networks Pioneer Award 2016, Prof. Dr. Volker Tresp, Principal Researcher Siemens and Roboy, an advanced humanoid robot.

----------------------------------------------------------------------

Our Rockstar Speakers

----------------------------------------------------------------------

1. Prof. Dr. Jürgen Schmidhuber, IDSIA

How to Learn an Algorithm (with Discussion)

Our general problem solvers search the space of algorithms running on general purpose computers with internal memory. Architectures include traditional computers, Turing machines, recurrent neural networks, fast weight networks, stack machines, and others. Some of our algorithm searchers are asymptotically time-optimal. Some are self-referential and can even learn the learning algorithm itself (recursive self-improvement). Some reinforcement-learn without a teacher to solve very deep algorithmic problems involving billions of steps. And algorithms learned by our Long Short-Term Memory recurrent networks defined the state-of-the-art in handwriting recognition, speech recognition, natural language processing, machine translation, image caption generation, etc. Google and others made them available to a billion users.

Biography

Since age 15 or so, Prof. Jürgen Schmidhuber's goal (http://www.idsia.ch/~juergen/optimalscientist.html) has been to build a self-improving Artificial Intelligence (http://www.idsia.ch/~juergen/ai.html) (AI) smarter than himself, then retire. He has pioneered self-improving general problem solvers (http://www.idsia.ch/~juergen/metalearner.html) since 1987, and Deep Learning Neural Networks (NNs) (http://www.idsia.ch/~juergen/deeplearning.html) since 1991 (http://www.idsia.ch/~juergen/firstdeeplearner.html). The recurrent NNs (http://www.idsia.ch/~juergen/rnn.html) developed by his research groups at the Swiss AI Lab IDSIA (http://www.idsia.ch/) & USI (http://search.usi.ch/people/855dfcba3eaf6e94156db5ff991ba300/Schmidhuber-Juergen) & SUPSI (http://www.supsi.ch/?page=English) (ex-TU Munich (http://people.idsia.ch/~juergen/tumcs.html) CogBotLab (http://people.idsia.ch/~juergen/cogbotlab.html)) were the first to win official international contests. They recently helped to improve connected handwriting recognition (http://www.idsia.ch/~juergen/handwriting.html), speech recognition, machine translation, optical character recognition, image caption generation,and are now in use at Google, Microsoft, IBM, Baidu, and many other companies. Two of the first four members of DeepMind (http://www.idsia.ch/~juergen/naturedeepmind.html) (sold to Google for over 600M) were PhD students in his lab. IDSIA's Deep Learners (http://www.idsia.ch/~juergen/deep-learning-overview.html) were also the first to win object detection (http://www.idsia.ch/~juergen/deeplearningwinsMICCAIgrandchallenge.html) and image segmentation contests (http://www.idsia.ch/~juergen/deeplearningwinsbraincontest.html), and achieved the world's first superhuman visual classification (http://www.idsia.ch/~juergen/superhumanpatternrecognition.html) results, winning nine international competitions (http://www.idsia.ch/~juergen/deeplearning.html) in machine learning & pattern recognition (more than any other team). They also were the first to learn control policies directly from high-dimensional sensory input using reinforcement learning. (http://www.idsia.ch/~juergen/compressednetworksearch.html) His research group also established the field of mathematically rigorous universal AI (http://www.idsia.ch/~juergen/unilearn.html) and optimal universal problem solvers (http://www.idsia.ch/~juergen/goedelmachine.html). His formal theory of creativity & curiosity & fun (http://www.idsia.ch/~juergen/creativity.html) explains art, science, music, and humor. He also generalized algorithmic information theory (http://www.idsia.ch/~juergen/kolmogorov.html) and the many-worlds theory of physics (http://www.idsia.ch/~juergen/computeruniverse.html), and introduced the concept of Low-Complexity Art, the information age's extreme form of minimal art. Since 2009 he has been member of the European Academy of Sciences and Arts. He has published 333 peer-reviewed papers (http://www.idsia.ch/~juergen/onlinepub.html), earned seven best paper/best video awards, the 2013 Helmholtz Award of the International Neural Networks Society, and the 2016 IEEE Neural Networks Pioneer Award (http://www.idsia.ch/~juergen/nnpioneeraward.html). He is also president of NNAISENSE (https://nnaisense.com/), which aims at building the first practical general purpose AI.

2. Prof. Dr. Volker Tresp, Siemens

Deep Learning in Future Industry

Prof. Dr. Volker Tresp, one of Siemens’ top machine learning authorities and a computer science professor at Ludwig Maximillian University in Munich will give an introductory talk about the Impact of Deep Learning Technologies in Future Industry.

Biography

Prof. Volker Tresp received a Diploma degree from the University of Goettingen, Germany, in 1984 and the M.Sc. and Ph.D. degrees from Yale University, New Haven, CT, in 1986 and 1989 respectively. Since 1989 he is the head of various research teams in machine learning at Siemens, Research and Technology. He filed more than 70 patent applications and was inventor of the year of Siemens in 1996. He has published more than 100 scientific articles and administered over 20 Ph.D. theses. The company Panoratio is a spin-off out of his team. His research focus in recent years has been „Machine Learning in Information Networks“ for modelling Knowledge Graphs, medical decision processes and sensor networks. He is the coordinator of one of the first nationally funded Big Data projects for the realization of „Precision Medicine“. In 2011 he became aHonorarprofessor at the Ludwig Maximilian University of Munich where he teaches an annual course on Machine Learning.

3. Roboy, Humanoid Robot

Introducing Roboy - the Roboy Student Club

Roboy is an advanced humanoid robot (https://en.wikipedia.org/wiki/Humanoid_robot) that was developed at the Artificial Intelligence Laboratory (https://en.wikipedia.org/wiki/Artificial_Intelligence_Laboratory) of the University of Zurich (https://en.wikipedia.org/wiki/University_of_Zurich). Originally designed to emulate humans with the future possibility of helping out in daily environments, the 3D printed robot boy already played in a theatre, goes to school and fascinates the audience with his unique story.

----------------------------------------------------------------------

Our Rockstar Team (ACM Student Chapter Munich)

----------------------------------------------------------------------

David Dao

Iris Shih

Homa Rasouli

Diana Papyan

Hesam Rabeti

Eileen Zhang

Uwe Stoll

Frederik Diehl

Daffiny Lin

Thanks to ACM and our Faculty Advisor: Prof. Dr. Hof

--------------------------------------------------------------------

Our Rockstar Sponsors for this Event

--------------------------------------------------------------------

- Pizza: TNG Technology Consulting GmbH (http://www.tngtech.com/)

- Catering: TrustYou (http://www.trustyou.com/?lang=de)

- Beverages: Nvidia (http://www.nvidia.de/page/home.html)

- Flyers & Support: JetBrains (https://www.jetbrains.com/)

- Location: Computer Vision Group (https://vision.in.tum.de/)

- Support: Import.io (https://import.io/)

A big thanks in advance to our speakers and organisers!

We are looking forward to see you soon.

Best,

Iris Shih and David Dao

For the ACM Student Chapter Munich