2022-09-14-MATLABDay_SREC.pptx

1
© 2023 The MathWorks, Inc.
with help from > 100 MathWorkers
MATLAB Day - Introduction to MATLAB & Simulink
Sri Ramakrishna Engineering College
14th September 2022
Anand Mukhopadhyay, PhD
Customer Success Engineer
Education Team, MathWorks
amukhopa@mathworks.com
Niveitha Mohankumar
Customer Success Specialist
nmohanku@mathworks.com
Arul Selvan
Account Manager
aselvan@mathworks.com
Lokesh Kantam
Application Engineer
DesignTech Systems
lokesh.kantam@designtechsys.com
Senthuram R
Senior Manager, Sales
DesignTech Systems
senthuran.r@designtechsys.com
Niveitha Mohankumar
Customer Success Specialist
Lokesh Kantam
Application Engineer
DesignTech Systems
lokesh.kantam@designtechsys.com

3
Agenda
Time Outline
10:00 AM - 10:30 AM
10:40 AM - 12:30 PM
How to access MATLAB campus License & MATLAB Portal Demonstration.
MathWorks Resources for Students through Campus-Wide License.
MATLAB for Engineers
Introduction to MATLAB
Approaching Artificial Intelligence applications
Model Based Design approach
Hardware Integration workflows
Resources to get started
Briefing on:
1.On-ramp challenge
2.MATLAB Cody competition
Q/A
12:30-1:30pm Lunch Break
1:30-2:30 pm Onramp Challenge
Tea Break 2:30-2:40pm
2:40-3:30pm Cody Challenge

4
MathWorks Today
5000+
staff
in 31 offices around
the world
4 million+
users
in more than 185
countries
and profitable every year
Privately
held
Headquarters
Natick, MA USA Europe
France
Germany
Ireland
Italy
Netherlands
Spain
Sweden
Switzerland
UK
Asia-Pacific
Australia
China
India
Japan
Korea
North America
United States
businesses, governments, and
universities
100,000+

5
The leading environment for
technical computing
 The industry-standard, high-level
programming language for algorithm
development, numeric computation, data
analysis and visualization
The leading environment for modeling,
simulating, and implementing dynamic
and embedded systems
 Applications in controls, signal processing,
communications, physical modeling, and
other system engineering areas

6
Our software is used to design the products we rely on every day
Commercial Aircraft
Smartphones
Automobiles
Consumer Goods

7
Advanced Prosthetics
Autonomous Robots
Reusable Rockets
Clean Energy
And the breakthroughs transforming how we live, learn, and work

9
What is MATLAB?
 Used for:
– Numerical computation
– Data analysis and visualization
– Algorithm development and programming
– Application development and deployment
 High-level language
 Interactive development environment

10
Automate
Technical Computing Workflow
Share/Deploy
Applications &
Embedded Systems
Code generation
Reporting &
Documentation
Reporting
Deployment
& Scalability
Big Data, HPC
Explore & Analyze & Prototype
Algorithm
Development
Signal Processing
Statistics &
Machine Learning
Video Processing &
Computer Vision
Spreadsheets &
Data Analytics
Biological Sequence
Analysis
Text Analysis Modeling &
Simulation
Image Processing
Files
Access, Acquire
Access files
Software or Web
Code & Applications
Software, Web
Hardware &
Scientific Instruments
Data acquisition
Instrument control

11
MATLAB Live Script
Colleague with MATLAB
HTML PDF
EX1_Demo Live Script

13
Set-Up Instructions
 Set up a MathWorks account if you don’t have one
– please use Google Chrome browser
– go to https://www.mathworks.com/mwaccount/
 Copy the materials via the MATLAB Drive
– go to https://drive.matlab.com/sharing/62017db2-72c2-4629-9e70-818651a44e1c
– Click on Add to my Files/Copy Folder
– You should see a separate folder saying “Owned By: Me” (on the right-hand side)

14
Get Demo files from MATLAB Drive
Step 1
Step 2

15
Agenda
Time Outline
10:00 AM - 10:30 AM
10:40 AM - 12:30 PM
Briefing on:
1.On-ramp challenge
Q/A

16
What is AI?
1950s 2015
Artificial Intelligence: The ability of a computer to perform tasks
commonly associated with intelligent beings like learning or problem-solving.
Machine Learning: Learning a task from data without relying on a
predetermined equation. (User may need to provide data features.)
Deep Learning: Learning from raw data without
predetermined features using neural networks with many layers

17
is a Leader in the 2021 Gartner
Magic Quadrant for Data Science
and Machine Learning Platforms for
the Second Year in a Row
Gartner Magic Quadrant for Data Science and Machine Learning Platforms, Peter Krensky, Carlie Idoine, Erick Brethenoux, Pieter den Hamer, Farhan Choudhary, Afraz Jaffri, Shubhangi Vashisth,1st March 2021.
This graphic was published by Gartner, Inc. as part of a larger research document and should be evaluated in the context of the entire document. The Gartner document is available upon request from MathWorks.
Gartner does not endorse any vendor, product or service depicted in its research publications, and does not advise technology users to select only those vendors with the highest ratings or other designation. Gartner research
publications consist of the opinions of Gartner research organization and should not be construed as statements of fact. Gartner disclaims all warranties, express or implied, with respect to this research, including any
warranties of merchantability or fitness for a particular purpose.

18
Evolution of Artificial Intelligence in MATLAB
2016 2017 2018 2019 2020
• CNNs
• Pretrained
Models
• Caffe Importer
Name Change
• Neural Network Toolbox
to Deep Learning Toolbox
Algorithms
• LSTMs
• Directed Acyclic Graphs
• Multi-GPU Training
Code Generation
• GPU Coder
Apps
• Image Labeler
Interoperability
• TensorFlow-Keras
Importer
Examples
• Signal Processing
• Audio
• Text Analytics
Algorithms
• Wavelet Scattering
Code Generation
• MATLAB Coder C++
Apps
• Deep Network Designer
• Video Labeler
• Audio Labeler
Interoperability
• ONNX Support
• Reinforcement Learning
Algorithms
• Automatic Differentiation
• Custom Training Loops
• Weight Sharing
• Big Image
Examples
• GANs
• Siamese Network
• Autoencoders
• 3-D support
• Explainable AI
• Occlusion
• Grad-CAM
Code Generation
• MATLAB Coder (ARM)
Apps
• Signal Labeler
• Deep Learning Data Sets
Apps
• Experiment Manager
• Lidar Labeler
Examples
• 5G / Wireless
• Lidar
• Over 200+ examples!
Algorithms
• Point Cloud
Explainable AI
• Lime
Code Generation
• Quantization
• Deep Learning HDL
Coder
Model Based Design
• Deep Learning in
Simulink
Before
2016
• Machine Learning
techniques
• “Shallow” neural
networks

19
MathWorks Focus on Deep Learning and AI for Engineering and
Science
Lidar
• Lidar Point Cloud Semantic Segmentation
• 3-D Object Detection Using PointPillars
Radar
• Radar Waveform Classification
• Pedestrian and Bicyclist Classification
Wireless Communications
• Modulation Classification
• Detect WLAN Router Impersonation
Reinforcement Learning
• Train Biped Robot to Walk
• PMSM Motor Control
Computational Finance
• Machine Learning for
Statistical Arbitrage
Medical Imaging
• 3-D Brain Tumor Segmentation
• Breast Cancer Tumor Classification
Audio
• Speech Command Recognition
• Cocktail Party Source Separation
Visual Inspection
• Manufacturing Defect Detection
• Anomaly Detection for Cloth Manufacturing
Automated Driving
• Deep Learning Vehicle Detector
• Occupancy Grid with Semantic Segmentation
Robotics
• Avoid Obstacles using
Reinforcement Learning
Predictive Maintenance
• Bearing Prognosis
• Pump Fault Diagnosis
Land-Use Classification
• Semantic Segmentation for
Multispectral Images
Reinforcement
Learning Toolbox™
Communications
Toolbox™
Phased Array
System Toolbox™
Lidar
Toolbox™
Image Processing
Toolbox™
Predictive Maintenance
Toolbox™
Image Processing
Toolbox™
Audio
Toolbox™
Automated
Driving Toolbox™
Robotics System
Toolbox™
Financial
Toolbox™
Image Processing
Toolbox™

20
Types of Machine Learning
Machine
Learning
Supervised
Learning
Regression
Classification
Develop predictive
model based on both
input and output data
Type of Learning Categories of Algorithms
Objective:
Easy and accurate computation of day-
ahead system load forecast

21
Machine
Learning
Supervised
Learning
Regression
Classification
Develop predictive
model based on both
Objective:
Train a classifier to classify human
activity from sensor data
Data:
Inputs 3-axial Accelerometer
3-axial Gyroscope
Outputs

22
Machine
Learning
Supervised
Learning
Regression
Classification
Unsupervised
Learning
Clustering
Develop predictive
model based on both
Discover an internal
representation from
input data only
Objective:
Given data for engine speed and
vehicle speed, identify clusters

23
Machine
Learning
Supervised
Learning
Regression
Classification
Unsupervised
Learning
Clustering
Type of Learning Categories of Algorithms Examples of Models
Support
Vector
Machines
Discriminant
Analysis
Naïve
Bayes
Nearest
Neighbor
Neural
Networks
Linear
Regression,
GLM
SVR, GPR
Ensemble
Methods
Decision
Trees
Neural
Networks
Neural
Networks
K-Means,
K-Medoids
Hierarchical
Gaussian
Mixture
Hidden
Markov
Model
Deep Learning
Reinforcement
Learning

24
Machine Learning and Deep Learning Datatypes
Signal
Image
Text
Numeric

25
MATLAB Apps
 Apps Tab in MATLAB
 Ease Most Used Functions across Domains
 Good for Learning and Demonstrating Concepts
 Creating an App/UI in MATLAB

26
App Designer
1. Define UI layout
2. Drag & Drop UI elements
3. Develop code for auto-generated
callbacks
https://in.mathworks.com/videos/app-designer-overview-
1510748719083.html

27
Agenda
Time Outline
10:00 AM - 10:30 AM
10:40 AM - 12:30 PM
Briefing on:
1.On-ramp challenge
Q/A

28
What is Simulink?
 Block-diagram environment
 Model, simulate, and analyze multi-domain
systems
 Design, implement, and test:
– Control systems
– Signal processing systems
– Communications systems
– Other dynamic systems
 Platform for Model-Based Design

29
Design Platform for full Development Process
INTEGRATION
TEST
AND
VERIFICATION
RESEARCH REQUIREMENTS
DESIGN
IMPLEMENTATION
MCU DSP FPGA ASIC
VHDL,
Verilog
C, C++
Structured
Text
PLC
Link design and
requirements
Save time and
reduce risk with
automatic code
generation
Optimise system-
level performance
Detect errors earlier
by testing earlier
Mechanical
Embedded
Software
Control
Electrical
Models & Simulation
Understand system
behavior by modeling
system and environment
in a single platform

30
Simulink is a block diagram environment for multidomain
simulation and Model-Based Design

31
MATLAB and Simulink Work Together
 Combine textual and graphical programming to design
your system
 Add MATLAB code into a Simulink block
 Create input data with MATLAB to drive model
simulations
 Run simulations in parallel
 Analyze and visualize data in MATLAB

36
Agenda
Time Outline
10:00 AM - 10:30 AM
10:40 AM - 12:30 PM
Briefing on:
1.On-ramp challenge
Q/A

37
Examples of MathWorks Supported Hardware
Arduino Lego EV3
Texas
Instruments
STM
Electronics Freescale
Raspberry Pi
BeagleBone
Black
Android/iOS
Devices
Kinect for
Windows
Zynq SDR
List of Supported Hardware: https://www.mathworks.com/hardware-support/home.html

38
Connect MATLAB and Simulink to Hardware
 Live Data Streaming to and from Hardware
 Generating Code and Targeting Hardware

39
Connect MATLAB and Simulink to Hardware
 Live Data Streaming to and from Hardware
 Generating Code and Targeting Hardware

40
Deploy MATLAB Algorithms on Raspberry Pi

41
Agenda
Time Outline
10:00 AM - 10:30 AM
10:40 AM - 12:30 PM
Briefing on:
1.On-ramp challenge
Q/A

42
Expert Trainers
Our instructors possess
unparalleled knowledge of
MathWorks products
Flexible Training
Over 50 courses available
around the world, at your
work site, or on the web
Proven Methods
Participants benefit from
real-world examples and
individualized attention
Advance your skills with MATLAB and Simulink courses
Get started for free with MATLAB Onramp, then build your skills with our self-paced
trainings and instructor-led courses.

43
MATLAB Academy Courses – Self-paced, Browser-based, with Certificates
Link to Courses

44
MATLAB Central
 Community for MATLAB and Simulink users
– Over 70k daily visits
 File Exchange
– Access more than 10k free files including
functions, apps, examples, and models
 MATLAB Answers
– Ask or search programming questions
– 18k+ community-answered Questions
 Blogs
– Read commentary from engineers who
design, build, and support MATLAB and Simulink

45
MathWorks Excellence in Innovation Projects
Accelerating the Pace of Engineering
Contribute to the progress of engineering and
science by solving key industry challenges!
mathworks/MathWorks-Excellence-in-Innovation:
Capstone and senior design projects

46
Additional resources
 MATLAB and Simulink Tutorials
 Self paced courses
 Videos and webinars
 Getting started with MATLAB Videos
 App Designer
 MATLAB Plot Gallery

47
Product Map
http://www.mathworks.com/products/pfo/

48
How can I get started with MATLAB and Simulink?
Videos and
Webinars
- Explore what’s
new
- Watch
demonstrations
- Applications /
Industries /
Capabilities
Tutorials
- Get started with
interactive
lessons
- Learn MATLAB
and Simulink
- Examples and
Exercises
MATLAB
Central
- Open exchange
for user
community
- MATLAB
Answers
- File Exchange
- Blogs by
MathWorkers
Onramps
- Online, Hands
On
- Exercises with
feedback
- Projects with
real world
applications
- 11 Onramps
available
Instructor Led
Trainings
- Customized
content
- Curriculum
paths
- Fundamentals /
Intermediate /
Advanced Levels
- 78 courses
available

49
Feedback form
For may further contact us with your queries:
Anand Mukhopadhyay
amukhopa@mathworks.com
Arul Selvan
aselvan@mathworks.com
Niveitha Mohankumar
Lokesh Kantam
Lokesh.kantam@designtechsys.
com
Senthuram R
senthuran.r@designtechsys.com
Feedback - https://tinyurl.com/srecmatlab

50
Agenda
Time Outline
10:00 AM - 10:30 AM
10:40 AM - 12:30 PM
Briefing on:
1.On-ramp challenge
Q/A

51
Onramp Challenge
https://in.mathworks.com/learn/tutorials/machine-learning-onramp.html
STEP 1
STEP 2
STEP 3

52
Cody Challenge
https://in.mathworks.com/matlabcentral/cody/groups/78
STEP 1
STEP 2
STEP 3

2022-09-14-MATLABDay_SREC.pptx

Recomendados

Recomendados

Mais conteúdo relacionado

Semelhante a 2022-09-14-MATLABDay_SREC.pptx

Semelhante a 2022-09-14-MATLABDay_SREC.pptx (20)

Último

Último (20)

2022-09-14-MATLABDay_SREC.pptx