Introduction to Artificial Neural Network

Course Content

Week 1

• Lecture 1 : Introduction to machine learning
  • What is Machine learning?
  • How it works?
  • How it is different from the conventional programming?
  • Different kinds of machine learning algorithms
    • Supervised learning
    • Unsupervised learning
    • Semi Supervised learning
    • Reinforcement learning
    • One shot learning
    • Few shot learning
    • Active learning
    • Incremental learning
• Lecture 2 : Introduction to machine learning (Cont.)
  • Different terimonologies
    • Artificial intelligence
    • Data science
    • Machine learning
    • Natural language processing
    • Computer vision
    • Predictive modelling
    • Generative AI
  • Different positions in Artificial intelligence
    • Data Scientist
    • ML Engineer
    • Data Engineer
    • MLOps (Machine Learning in Operations)
    • ML/DL/NLP Researcher
    • Gen AI expert

Week 2

• Lecture 3 : Introduction to Python
  • Setup & Installation
    • Installing Python and Setting Up the Environment
    • Introduction to Python IDEs (e.g., PyCharm, VS Code)
    • Hello World
  • Variables
    • Variables and Data Types (int, float, string, bool)
    • Type Conversion and Casting
    • Basic Operators (Arithmetic, Comparison, Logical)
    • Working with Strings and String Operations
  • Control Structures
    • Conditional Statements: if, elif, else
    • Loops: for, while
    • Nested Loops and Conditions
    • Break, Continue, and Pass Statements
• Lecture 4 : Python - Data Types
  • Data types
    • Lists: Creation, Indexing, Slicing, and Modifying
    • List Comprehensions
    • Tuples: Creation, Indexing, and Immutable Properties
    • Common List and Tuple Methods
    • Dictionaries: Key-Value Pairs, Accessing, Adding, and Modifying Data
    • Common Dictionary Methods
    • Sets: Creation, Operations, and Methods
    • Working with Complex Data Structures

Week 3

• Lecture 5 : Python - Functions and packages
  • Functions and packages
    • Defining and Calling Functions
    • Function Parameters and Return Values
    • Scope of Variables (Local and Global)
    • Introduction to Python Modules and Libraries
    • Importing and Using Modules
  • File Handling
    • Opening, Reading, and Writing Files
    • Working with Text Files
    • Handling File Exceptions
    • File Methods and Context Managers (with statement)
  • Introduction to OOP Concepts: Classes and Objects
    • Defining Classes and Methods
    • Inheritance and Polymorphism
    • Encapsulation and Abstraction
• Lecture 6 : Python - Data Analysis
  • Data Analysis
    • Introduction to Pandas and NumPy Libraries
    • Working with DataFrames and Series
    • Data Cleaning and Manipulation
    • Basic Data Visualization using Matplotlib

Week 4

• Lecture 7 : Supervised Machine Learning
  • Multi layer perceptron
    • Perceptron learning
    • Linear activation functions
    • Non-linear activation functions
• Lecture 8 : Loss Functions
  • Regression Loss
    • Mean Squared Error (MSE)
    • Mean Absolute Error (MAE)
    • Huber Loss
    • Log-Cosh Loss

Week 5

• Lecture 9 : Loss Functions (cont.)
  • Classification Loss
    • Binary Cross-Entropy
    • Categorical Cross-Entropy
    • Sparse Categorical Cross-Entropy
    • Kullback-Leibler (KL) Divergence
    • Hinge Loss
• Lecture 10 : Loss Functions (cont.)
  • Ranking Loss
    • Contrastive Loss
    • Triplet Loss
  • Other Specialized Loss
    • Cosine Similarity Loss
    • Focal Loss
    • Dice Loss

Week 6

• Lecture 11 : Activation Functions
  • Types of Activation Functions
    • Linear Activation Function
    • Step Function (Binary Thresholding)
    • Sigmoid Function (Logistic Activation)
    • Tanh (Hyperbolic Tangent) Function
    • Hard Sigmoid
• Lecture 12 : Activation Functions (Cont.)
  • Types of Activation Functions
    • Softmax
    • Swish
    • Maxout
    • ReLU (Rectified Linear Unit)
    • Leaky ReLU
    • Parametric ReLU (PReLU)
    • Exponential Linear Unit (ELU)

Week 7

• Lecture 11 : Optimizers
  • Types of Optimizers
    • Gradient Descent
    • Batch Gradient Descent
    • Stochastic Gradient Descent (SGD)
    • Mini-batch Gradient Descent
• Lecture 12 : Optimizers (Cont.)
  • Types of Optimizers
    • Momentum
    • Nesterov Accelerated Gradient (NAG)
    • Adagrad (Adaptive Gradient)

Week 8

• Lecture 13 : Optimizers (Cont.)
  • Types of Optimizers
    • RMSprop (Root Mean Square Propagation)
    • Adadelta
    • Adam (Adaptive Moment Estimation)
• Lecture 14 : Optimizers (Cont.)
  • Types of Optimizers
    • Adamax
    • AMSGrad
    • SGD with Warm Restarts (SGDR)

Week 9

• Lecture 13 : Model Validation
  • Cross-Validation
  • Leave-P-Out Cross-Validation
  • Bootstrap Sampling
  • Hold-Out Method
  • Confusion Matrix
• Lecture 14 : Model Validation (Cont.)
  • Receiver Operating Characteristic (ROC) Curve and AUC (Area Under the Curve)
  • Precision-Recall Curve
  • Log-Loss (Logarithmic Loss) / Cross-Entropy Loss
  • Mean Squared Error (MSE) and Root Mean Squared Error (RMSE)
  • Mean Absolute Error (MAE)

Week 10

• Lecture 15 : Model Validation (Cont.)
  • R-squared (Coefficient of Determination)
  • Adjusted R-squared
  • F-Score / F-Test
• Lecture 16 : Model Deployment
  • Overview of ML Model Deployment
  • Model Deployment Architectures (on Premise, Cloud, Hybrid)
  • Deployment Strategies
  • Deployment Workflow

Week 11

• Lecture 15 : Model Monitoring and Performance Metrics
  • Importance of Model Monitoring
  • Key Monitoring Metrics
  • Types of Monitoring
• Lecture 16 : Model Drift, Retraining, and Continuous Learning
  • Understanding Model Drift
  • Detecting Drift
  • Continuous Learning and Model Retraining
  • Tools for Retraining Pipelines

Week 12

• Lecture 17 : Model Tracking, Versioning, and Governance
  • Importance of Model Tracking and Versioning
  • Tools for Model Tracking
  • Model Versioning
  • Model Governance and Regulatory Compliance
• Lecture 18 : AI Ethics and Fairness
  • Introduction to AI Ethics
  • Fairness in AI
  • Bias in AI
  • Transparency and Explainability
  • Privacy and Data Protection