IEEE Kerala Section

Robotics and Automation Society in partnership with NASSCOM Kerala

Technical Talk on:
Develop and Deploy Deep Learning Algorithms Using MATLAB
By
Alka Nair
Application Engineer, MathWorks India

Date : 6th August 2018
Venue : NASSCOM Startup Warehouse, Infopark Campus, Kakkanad, Kochi
Time : 4:00 pm – 6:00 pm
Entry : Free

Speaker Profile:
Alka Nair is part of Application Engineering team at MathWorks focusing on technical computing. She has been working with customers to address their challenges using MathWorks products and services. Her areas of interest include Deep Learning, Autonomous Driving, High performance Computing, Image Processing and Computer Vision. She completed her MS in Electrical Engineering from Indian Institute of Technology, Madras specializing in the area of Image Processing and B. Tech from Calicut University.

Agenda & Abstract of the talk:
Designing and deploying machine learning and deep learning-based computer vision applications to embedded CPU and GPU platforms is challenging because of resource constraints inherent in embedded devices. A MATLAB® based workflow facilitates the design of these applications, and automatically generated C or CUDA® code can be deployed on boards like the Jetson TX2 and DRIVE™ PX to achieve very fast inference.
The session illustrates how to address these challenges in all the major phases of deep learning workflow. Starting with algorithm design, the algorithm may employ deep neural networks augmented with traditional computer vision techniques and can be tested and verified within MATLAB. Next, these networks are trained using GPU and parallel computing support for MATLAB either on the desktop, cluster, or the cloud. Finally, we automatically generate portable and optimized C/C++ and/or CUDA® code from the MATLAB algorithm, which is then cross-compiled and deployed to CPUs and/or a Tegra®board.

- Artificial Intelligence today
- Deep Learning Applications
- MATLAB – as a tool for rapid prototyping for analytics algorithm development
- How to build a deep learning model in a few lines of code
- Scaling up training and hyperparameter tuning
- Embedded deployment of deep learning algorithms

Interested IEEE Members (Students and Professionals) shall register here: http://bit.ly/ieeerasdl

For queries, contact
Sahil Sameer
sahilsameer@ieee.org
+91 8714823928

---

E-notice circulated on behalf of IEEE RAS Kerala Chapter

Follow IEEE Kerala Section:

Facebook | Twitter | LinkedIn | Instagram