AIRTIFICIAL INTELLIGENCE AN
S.No: Day Forenoon
Theory
Introduction to AI
& MLWhat is AI,
1 DAY-1 Types of AI,
Applications of AI,
Advantages and disadvantages of AI
Introduction to ML,
Types of Ml algorithms :
Theory & Excercise / Workout
Machine Learning
Workflow, Introduction to Computer
Vision & its applications |
2 DAY-2
Theory & Excercise / Workout
Regression Algorithms:
Introduction to regression,
Types of regression :
Linear regression :
i)Simple linear regression
ii) Multiple linear
3 DAY-3 regression, Logistic regression,
Overfitting & Underfitting in Machine
Learning
Break
Theory & Excercise / Workout
4 DAY-4
Brea
Classification Algorithms :
Introduction to classification,
Support vector Machine (SVM),
4 DAY-4 Types of SVM : linear SVM & non-linear
SVM,
K-nearest neighbour (KNN)
Theory & Excercise / Workout
Clustering
Algorithms:Introduction to clustering,
5 DAY-5 Types of clustering : Hierarchical
clustering (Agglomerative & divisive
clustering) ,
Partitioning clustering ( K-means
clustering)
Practical (Lab Session)
6 DAY-6 live project:Label reading using Optical
Character Recognition
** Note : laptop or dekstop with webcam for live project,good internet
AIRTIFICIAL INTELLIGENCE AND MACHINE LEARNING
Forenoon Afternoon
Practical (Lab Session) Theory & Excercise/Workout
Python Installation ,
Setting Environmental variable
Supervised learning -
configuration,
Unsupervised learning -
Basics of Python Programming,
Reinforcement learning
(Data structure, Control
statements, Function) ,
Theory & Excercise / Workout Practical (Lab Session)
Data collection , Overview on CV libraries ,
Data preprocessing, installation Basic programs on Computer
Choosing the learning algorithms, vision
Training the model,
Evaluating the model,
Predictions.
Practical (Lab Session) Practical (Lab Session)
Introduction to
Deep Learning
(DL) and
Artificial Neural
Implementation of linear
Network (ANN),What is DL, Artificial Neural
Lunch Break
regression,Implementation of
Network (ANN) : Working of ANN - Activation
logistic regression
function (Sigmoid, Tanh,
ReLU) -
Break
Learning process of ANN - Forward
propagation - Backward propagation
Theory & Excercise / Practical(lab sesson) Practical (Lab Session)
Lunc
Break
Working of KNN, Advantages and Implementation of Support
disadvantages of KNN, Vector Machine,
Applications of KNN, Implementation of K-nearest neighbour
Confusion matrix,Convolutional
Neural Network (CNN),
Introduction to CNN, Types of CNN,
Theory & Excercise / Workout Practical (Lab Session)
project:Implementation of hierarchical
live project:Object Tracking based on Color
clustering,
with OpenCV ,
project:Implementation of
Live project:Face Recognition with OpenCV
K-means clustering
Practical (Lab Session) Practical (Lab Session)
live project:License Plate Recognition
PROJECT PRESENTATION
System
ive project,good internet
Afternoon
Practical (Lab Session)
Numpy,
Matplotlib, Pandas,
Project:CHATBOT CREATION
Practical (Lab Session)
Basics of data data cleaning and
data preprocessing
Practical (Lab Session)
live project:Moving Object Detection
using OpenCV
Practical (Lab Session)
live project:Advanced Face Detection
and Tracking
Practical (Lab Session)
live project:Recognizing Emotions from
Faces ,
Practical (Lab Session)
Material, interview question and
answers sharing and Assessment
