Sona College of Technology (Autonomous), Salem – 636 005
Department of Information Technology
ADVANCED DIPLOMA / CERTIFICATION PROGRAMME
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
CURRICULUM & SYLLABI
Academic year – 2021-22
Semester 1:
S.NO Topics Covered Credits
1 Introduction to AI 1
2 Python for Data Science 2
3 Data Wrangling Techniques 2
4 Introduction to Neural Networks 1
5 TensorFlow & Keras 2
6 Capstone Project I 2
Total 10
Semester 2:
S.NO Topics Covered Credits
1 Convolutional Neural Networks 2
2 Recurrent Neural Networks 2
3 Natural Language Processing 2
4 Build & Deploy an AI Application 1
5 Practical AI Example 1
6 Capstone Project II 2
Total 10
Semester 3:
S.NO Topics Covered Credits
1 Fundamentals of Machine Learning 2
2 Mathematics and Statistics 2
3 Methods and Algorithms in ML (Supervised Learning) 4
4 Capstone Project III 2
Total 10
Semester 4:
S.NO Topics Covered Credits
1 Methods and Algorithms in ML (Unsupervised) 3
2 Hyperparameter Tuning and Validation 3
3 Recommendations Systems 2
4 Capstone Project IV 2
Total 10
ADVANCED DIPLOMA / CERTIFICATION PROGRAMME
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
SYLLABUS
Semester I:
Module 1: Introduction to Artificial Intelligence:
Introduction to AI
Intelligent Agents
Search Methods and Knowledge Representation
Use Cases of Artificial Intelligence
Role of Machine Learning Engineer
Machine Learning Tools & Packages
Module 2: Python for Data Science
Python Data Structures
Python Programming Fundamentals
Conditions and Branching
Loops
Functions
Python Packages
Working with NUMPY
Working with Pandas
Introduction to Data Visualization
Introduction to Matplotlib and Seaborn
Basic Plotting with Matplotlib and Seaborn
Module 3: Data Wrangling Techniques
Introduction to Data pre-processing
Importing the Dataset
Handling Missing data
Working with Categorical Data
Splitting the data into Train and Test set
Feature Scaling
Module 4: Introduction to Neural Networks
The Neuron
The Activation Function
How do Neural Networks work?
How do Neural Networks learn?
Gradient Descent
Stochastic Gradient Descent
Backpropagation
Module 5: TensorFlow & Keras
Introduction to TensorFlow & Keras Framework
Introduction to the Sequential Mode
Activation functions
Layers
Training
Loss function
Building ANN Using Tensor flow
Evaluating Improving and Tuning ANN
Capstone Project I
Semester II
Module 6: Convolutional Neural Networks
Introduction to Convolutional Neural Networks
What are convolutional neural networks?
Step 1 - Convolution Operation
Step 1(b) - ReLU Layer
Step 2 - Pooling
Step 3 - Flattening
Step 4 - Full Connection Classification of images using CNN
Evaluating, Improving, and Tuning the CNN
Module 7: Recurrent Neural Networks
Introduction to Recurrent Neural Networks
The idea behind Recurrent Neural Networks
The Vanishing Gradient Problem
LSTMs
LSTM Variations Predicting Google stock prices using RNN
Evaluating, Improving, and Tuning the RNN
Module 8: Natural Language Processing
Introduction to Natural Language Processing
Introduction to NTLK
Bag of Words model
Natural Language Processing in Python
Sentiment analysis using Natural Language Processing
Module 9: Practical AI Examples:
Fare Prediction for Uber
Test bench time reduction for Mercedes-Benz
Products rating prediction for Amazon
Demand Forecasting for Walmart
Improving customer experience for Comcast
Attrition Analysis for IBM
NYC 311 Service Request Analysis
Movie Lens Dataset Analysis
Stock Market Data Analysis
Module 10: Build & Deploy an AI Application
Introduction to different modes of Deployments
Working with Flask framework
Building an application with Flask Framework
Integrating Deep learning model with Web Application
Capstone Project II
Semester III
Module 11: Fundamentals of Machine Learning
Usecase1: Facebook Auto-Tagging/Face Recognition in Mobiles
Usecase2: Google Assistant
Usecase3: Youtube/Netflix/Amazon Recommendation Systems
Usecase4: Dynamic Pricing in Travel
Usecase5: Google Translate
Usecase6: Gmail Spam Detection
Usecase7: Sophia a social humanoid robot
Module 12: Mathematics & Statistics
Introduction to Probability
Mean, Median,Mode,Variance,Standard Deviation
Quantiles
Gaussian (Normal) Distribution, Skew Distribution
Covariance and Correlation
Linear Regression
Logistic Regression
Naïve Bayes Classifier
Bias-variance trade-off
Dimensionality reduction using Principal component Analysis
Time Series Forecasting
Hands-on Lab
Module 13: Methods and Algorithms in Machine Learning Part I (Supervised Learning)
Supervised Learning
Regression
o Simple Linear Regression
o Multi Linear Regression
o Polynomial Regression
o Decision Tree
o Random Forest
Classification
o Logistic Regression
o K-Nearest Neighbours
o Support Vector Machine
o Naive Bayes
o Decision Tree
o Random Forest
Hands-on Lab
Capstone Project III
Semester IV
Module 14: Methods and Algorithms in Machine Learning (PART-2)
Unsupervised Learning
K-Means Clustering
Hierarchical Clustering
Ridge Regression
XGBoost Algorithm
Hands-on Lab
Module 15: Hyper parameters Tuning & Validation
Grid Search
Randomized Search
Cross Validation
Hyperparameter Tuning and Model Selection
Hands-on Lab
Module 16: Recommendation Systems
Collaborative Recommender System
Content Based Recommender System
Hands-on Lab
Capstone Project IV
