Explore the comprehensive ML Campaign by GDSC MMCOE, spanning 4 days of immersive learning.
From foundational ML concepts to cutting-edge topics like Deep Learning, Gen AI, and Computer Vision, this PPT contains all the content that was used to teach various topics of AIML in 4 days of ML Campaign
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
GDSC MMCOE - ML Campaign
1. Lead (2023-24):
Ms. Swapnali Morankar
Google Developer Student Clubs
Marathwada Mitra Mandal's College of Engineering
Karvenagar, Pune
LEARN CONNECT GROW
5. Meet our AI/ML Team
Mr. Parth Solanke (Head)
Mr. Aditya Purohit (Co-Head)
Mr. Anish Dhanorkar (Auditor)
Ms. Samruddhi Bhabad (Member)
Mr. Lavesh Akhadkar (Member)
Ms. Vaishnavi Shinde (Member)
Mr. Tejas Mankeshwar (Member)
6. Overview of Campaign
6th Feb 2024
Introduction to
Deep Learning
Logistic Regression
TensorFlow
8th Feb 2024
Introduction to
Computer Vision
Face Recognition,
Image Classification
7th Feb 2024
Introduction to
GEN AI
Google Bard and
Gemini
5th Feb 2024
Introduction to
Machine Learning
Linear Regression
Pandas
38. WHAT IS COMPUTER VISION?
Computer vision (CV) is a field of computer
science that focuses on enabling computers to
identify and understand objects and people in
images and videos.
Like other types of AI, computer vision seeks to
perform and automate tasks that replicate
human capabilities. In this case, computer
vision seeks to replicate both the way humans
see, and the way humans make sense of what
they see.
Basically computer vision allows the computer
to process raw image data and extract useful
information from this raw data
42. HOW DO YOU WORK WITH IMAGE DATA?
There are various data types in image processing,
e.g., uint8, uint16, single precision, double
precision, logical, and char.
Various libraries such as OpenCV allow us to work
with images and manipulate data that is images.
These libraries are very well documented and are
generally open source this results in very robust
behavior
43. HOW TO DETECT EDGES?
Canny Edge Detection:
It is a five step algorithm to detect edges
in images, developed in 1986.
Algorithm for Canny Edge Detection :
Noise Reduction
Gradient Calculation
Non maximum suppression
Double Threshold
Edge Tracking by Hysteresis
BUT WHY?
Feature extraction
Feature Extraction is a process in
machine learning and data analysis that
involves identifying and extracting
relevant features from raw data.
These features are later used to create
a more informative dataset, which can
be further utilized for various tasks
such as: Classification, Prediction, etc.