Exclusive MATLAB Seminar

“Demystifying Deep Learning - A practical Approach in MATLAB”

Techsource Engineer, Ms. Siti Safwana


Universiti Malaysia Perlis | 17 April 2019 | 9.00am to 12.30pm


in collaboration with:

Date : 17 April 2019

Time: 9.00am - 12.30pm

Venue: Bilik Mesyuarat Utama, Pusat Pengajian Kejuruteraan Mekatronik, UNIMAP.


Presenter:  Ms. Siti Saftwana , Application Engineer, Techsource Systems.

Topic 1 : 9.00 am to 10.30 am - What's New in MATLAB

Are you using MATLAB to its fullest potential?

MATLAB has changed significantly over the last 3 years to address the growing needs of our users, but we've noticed that even experienced MATLAB users aren't taking advantage of our latest and greatest features.

This seminar will cover the newest MATLAB features and show you how to utilize these features to simplify your work, save time, and increase your productivity.

Highlights include:
•   MATLAB Foundation Updates
           o   Faster execution engine
           o   Graphics system
           o   Live Editor
•   Data handling and language enhancements
           o   Simpler data importing
           o   Improved datatypes
           o   Big data capabilities
•   App building
           o   App Designer
           o   Sharing apps and creating toolboxes
•   Hardware support
•   Other Toolbox enhancements

Topic 2:  10.45am - 12.30pm - Demystifying Deep Learning: A practical approach in MATALB

In this seminar, we’ll demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. In doing so, we’ll decipher practical knowledge of the domain of deep learning.  We’ll build and train neural networks that recognize handwriting, classify food in a scene, and figure out the drivable area in a city environment. 
Along the way, you’ll see MATLAB features that make it easy to:

Manage extremely large sets of images

  • Visualize networks and gain insight into the black box nature of deep networks

  • Perform classification and pixel-level semantic segmentation on images

  • Import training data sets from networks such as GoogLeNet and ResNet

  • Import and use pre-trained models from TensorFlow and Caffe

  • Speed up network training with parallel computing on a cluster

  • Automate manual effort required to label ground truth

Speaker Profile

Ms. Siti Safwana

Application Engineer, TechSource

Siti Safwana is an Application Engineer at TechSource Systems. She is specialized in the field of image processing, computer vision, machine learning and deep learning with MATLAB. Before joining TechSource Systems in 2018, he worked at Techloyce in Selangor as an CRM and ERP Consultant in IT field.


Siti Safwana holds a BEng in Computer Communication System Engineering from Universiti Putra Malaysia. She doing research in 2 years in computer vision (depth/disparity map) for her MEng project at Universiti Teknikal Malaysia Melaka under department of Faculty of Electronic and Computer Engineering