Fundamentals of Deep Learning for Multiple Data Types
Date: | Friday, March. 15, 2019, 9:00-17:30 |
---|---|
Location: | LRZ Building, Garching/Munich, Boltzmannstr. 1, LRZ Hörsaal H.E.009 & Seminarraum 1 H.E.008 |
Contents: |
The Leibniz Supercomputing Center (LRZ) is the computer center for Munich's universities and for the Bavarian Academy of Sciences and Humanities.It is also a national center for High Performance Computing. NVIDIA Deep Learning Institute (DLI) offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning. LRZ and DLI are excited to announce this one-day practical workshop - Fundamentals of Deep Learning for Multiple Data Types at LRZ on March. 15th, 2019, exclusively for verifiable students, staff, and researchers from any academic institutions (For industrial participants, please contact NVIDIA for industrial specific training). In this full-day workshop, you’ll learn how to train a network using TensorFlow and the MSCOCO dataset to generate captions from images and video by:
Upon completion, you’ll be able to solve deep learning problems that require multiple types of data inputs. Workshop Agenda: 9:00 Lecture
9:45 Break 10:00 Image Segmentation with TensorFlow (with coffee break) 12:00 Lunch 1:00 Word Generation with TensorFlow 3:00 Break 3:15 Image and Video Captioning by Combining RNNs with CNNs 5:15 Closing Comments & Questions 5:30 End Content level: Beginner Pre-Requisites: complete DLI computer vision workshop or have completed a university machine learning course, familarity with TensorFlow will be a plus as all the hands-on sessions are using TensorFlow. For those who do not program in TensorFlow, please go over TensorFlow tutorial: https://www.tensorflow.org/tutorials/, especially the "Learn and use ML" section. IMPORTANT: To reserve your seat, you MUST register at the LRZ registration with a valid email address. Please choose course HDLW3W18. Additionally, please follow these pre-workshop instructions:
On the day of the workshop, please bring your student/academia id. The number of participants is limited to 100.
Looking forward to seeing you at LRZ. The NVIDIA Deep Learning Institute delivers hands-on training for developers, data scientists, and engineers. The program is designed to help you get started with training, optimizing, and deploying neural networks to solve real-world problems across diverse industries such as self-driving cars, healthcare, online services, and robotics. |
Language: | English |
Teacher: | Dr. Yu Wang, LRZ and Nvidia University Ambassdor |
Registration: | Via the LRZ registration form. Please choose course HDLW3W18. |