Breadcrumb Navigation
2020-02-12 Deep Learning: A Practical Approach in MATLAB (09:00-12:30)
Introduction to deep learning with MATLAB.
Tabs
About this training
Demystifying Deep Learning: A Practical Approach in MATLAB
Are you new to Deep Learning and want to learn how to apply these techniques in your work?
Deep Learning achieves human-like accuracy for many tasks considered algorithmically unsolvable with traditional Machine Learning. It is frequently used to develop applications such as face recognition, automated driving, and image classification.
The main tasks are to assemble large data sets, create a neural network, to train, visualize, and evaluate different models, using specialized hardware - often requiring unique programming knowledge. These tasks are frequently even more challenging because of the complex theory behind them.
We will demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. In doing so, we will demystify practical knowledge of the domain of Deep Learning.
Highlights / Learning Outcomes
Are you new to Deep Learning and want to learn how to apply these techniques in your work?
Deep Learning achieves human-like accuracy for many tasks considered algorithmically unsolvable with traditional Machine Learning. It is frequently used to develop applications such as face recognition, automated driving, and image classification.
The main tasks are to assemble large data sets, create a neural network, to train, visualize, and evaluate different models, using specialized hardware - often requiring unique programming knowledge. These tasks are frequently even more challenging because of the complex theory behind them.
We will demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. In doing so, we will demystify practical knowledge of the domain of Deep Learning.
Highlights / Learning Outcomes
- Introduction to Deep Learning and its use cases
- Perform classification on images and time series
- Import and use pre-trained models
- Build a deep network that can classify your own handwritten digits
- Speed up network training with parallel computing on multiple CPUs/GPUs
- Learn how to use CUDA code generation technology to accelerate inference performance on a GPU
- UNIBE staff members, students and potential users involved in scientific research
- Engineers, scientists and anybody interested in the development of Deep Learning applications.
- Participants must bring own laptops and should have a minimal experience with Python, MATLAB, R or similiar tools. Mathematics on an introductionary university level is needed.
- Participants must be able to login to the UBELIX cluster (via ssh on MAC or Linux, via Putty or something else on Windows) where we have our MATLAB installations. If this is new to you, you may consider attending the HPC introduction training: https://ilias.unibe.ch/goto.php?target=crs_1402720&client_id=ilias3_unibe
- The training alternates between short theoretical introductions and programming exercises.
- A certificate will be delivered to participants who have attended the whole training.
- From MathWorks.
Practical information (time, location ...)
Time : 2020-02-12 09:00 - 12:30
Location : Mittelstrasse 43, room 124, University of Bern
Training language: English
Participants : Max 24
Registraion : Mandatory
Coaches : Dr. Matthias Summer (Application Engineer at MathWorks), PD Dr. Sigve Haug (responsible)
Prerequisites : Laptop, minimal programming experience
Certificate : Certificate for full training attendance
Location : Mittelstrasse 43, room 124, University of Bern
Training language: English
Participants : Max 24
Registraion : Mandatory
Coaches : Dr. Matthias Summer (Application Engineer at MathWorks), PD Dr. Sigve Haug (responsible)
Prerequisites : Laptop, minimal programming experience
Certificate : Certificate for full training attendance
About ScITS
Matthias Sommer is Application Engineer at https://ch.mathworks.com/de/company/aboutus/directions/bern--switzerland.html.
The Science IT Support is there to boost your research by supporting you solving computing challenges.
Your code doesn't compile, you need more computing power, more storage, a data mangament plan and
so on - drop an email, call or pass by our office. Cheers, Sigve
Our webpage is http://scits.unibe.ch/
The Science IT Support is there to boost your research by supporting you solving computing challenges.
Your code doesn't compile, you need more computing power, more storage, a data mangament plan and
so on - drop an email, call or pass by our office. Cheers, Sigve
Our webpage is http://scits.unibe.ch/
