0% found this document useful (0 votes)
2 views5 pages

Course Modules Compiled

The document outlines a comprehensive 25-module course covering essential topics in AI and machine learning, including mathematics fundamentals, SQL, Python, exploratory data analysis, and various machine learning paradigms. It also delves into advanced techniques such as neural networks, reinforcement learning, and deployment strategies, culminating in a capstone project for practical application. The course aims to equip participants with the knowledge and skills necessary for industry readiness in AI and machine learning.

Uploaded by

ikixdesignteam
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
2 views5 pages

Course Modules Compiled

The document outlines a comprehensive 25-module course covering essential topics in AI and machine learning, including mathematics fundamentals, SQL, Python, exploratory data analysis, and various machine learning paradigms. It also delves into advanced techniques such as neural networks, reinforcement learning, and deployment strategies, culminating in a capstone project for practical application. The course aims to equip participants with the knowledge and skills necessary for industry readiness in AI and machine learning.

Uploaded by

ikixdesignteam
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Course Outline: Modules 1 to 25

Module 1: Introduction to the Programme


 Overview of topics to be covered in the Programme
 Motivation for the Programme
 Overview of the Programme
 Expected Outcomes of the Programme
 Brief about software/tools

Module 2: Mathematics Fundamentals


 Linear Algebra: Vectors, matrices, inner products, matrix-vector multiplication,
eigenvalues/vectors, singular value decomposition
 Calculus: Differentiation (single/multiple variables, vectors, and matrices),
unconstrained and constrained optimisation (Lagrangian multiplier)
 Probability Theory: Discrete and continuous random variables, probability
distributions, Bayes' rule, Gaussian density function, conditional probability
 Statistics: Descriptive and inferential statistics, hypothesis testing, probability
distributions

Module 3: SQL Fundamentals


 SQL Basics: RDBMS & NoSQL, MS SQL Server & MongoDB demos, SQL tables, joins,
subqueries, views, functions, pattern matching, UDFs, stored procedures, ranking,
sorting
 Advanced SQL: Mathematical and date-time functions, SQL ROLLUP, record grouping,
common table expressions, clustered indexes
 Data Pipeline Integration: Integrating ML models into data pipelines

Module 4: Python Fundamentals


 Python: Pre-requisites: Python syntax, factors, NumPy, SciPy, Pandas, Data
Visualization, Scikit Learn, Python Multiprocessing, Seaborn, TensorFlow
 Deployment and productionization
 Advanced Python Techniques: Generators, iterators, decorators, context managers
 Performance Optimization Techniques: Demo on Python types, Python packages,
Python C-extensions
 Learn TensorFlow
 Demo of deployment on Python
 Demo on advanced Python techniques

Module 5: Exploratory Data Analysis (EDA)


 Data types and variables; central tendency and dispersion
 Five-point summary and skewness; box plot; covariance and correlation
 Encoding, scaling, and normalization
 Focus on preprocessing: missing values, working with outliers
 Demo on EDA

Module 6: Applications of AI and ML


 NLP and Text Processing Applications: Text classification, part-of-speech tagging,
named entity recognition, text summarization, question answering, matching,
translation
 Demo on sentiment analysis, chatbot creation, text-to-text translation
 Image and Video Processing Applications: Image classification, object detection, face
recognition, video captioning, visual question answering, virtual agent, game creation
 Speech Processing Applications: Speech recognition, speaker recognition, speech
synthesis, speech-to-speech translation, spoken language recognition, text-to-speech
synthesis

Module 7: Paradigms of Machine Learning


 Supervised learning
 Unsupervised learning
 Semi-supervised learning
 Active learning
 Self-supervised learning
 Transfer learning
 Domain adaptation
 Zero-shot, One-shot, Few-shot learning
 Federated learning

Module 8: Regression Methods


 Linear model for regression
 Supervised learning
 Parameter estimation
 Overfitting
 Regularisation
 Ridge regression

Module 9: Probabilistic Models for Classification


 K-nearest neighbour classifier
 Bayes classifier
 Normal density function
 Decision surfaces
 Naive Bayes classifier
 Maximum likelihood estimation
 Gaussian mixture model

Module 10: Support Vector Machines for Classification


 Distance of a point to a hyperplane
 Margin of a separating hyperplane
 Hard-margin SVM
 Soft-margin SVM
 Kernel functions
 Multi-class classification using SVMs

Module 11: Dimension Reduction Techniques


 Principal component analysis
 Fisher discriminant analysis

Module 13: Ensemble Methods


 Bagging
 Boosting
 AdaBoost
 Applications of Ensemble Methods

Module 14: Clustering Techniques


 K-Means Clustering
 Hierarchical Clustering
 Applications of Clustering Techniques

Module 15: Multilayer Feedforward Neural Networks for Classification and


Regression
 McCulloch-Pitts Neuron
 Perceptron Learning Rule
 Sigmoid Activation Function
 ReLU Activation Function
 Softmax Activation Function
 Multilayer Feedforward Neural Network
 Error Backpropagation Method
 Gradient Descent Method
 Stochastic Gradient Descent Method
 Stopping Criteria
 Logistic Regression-Based Classifier
 Focus: Deep Learning using TensorFlow and Keras, understanding feedforward neural
networks, backpropagation, gradient descent, and logistic regression

Module 16: Deep Feedforward Neural Networks


 Generalized Delta Rule
 Adam-Based Optimizer
 Regularization Techniques: Dropout, Dropconnect, Batch Normalization

Module 17: Convolutional Neural Networks (CNNs)


 Basic CNN Architecture
 Rectilinear Unit (ReLU)
 2D Deep CNNs: LeNet, VGGNet, GoogleNet, ResNet
 Image Classification using 2D CNNs
 3D CNN for Video Classification
 Object Localization and Detection Algorithms – YOLO
 Image Segmentation and UNet

Module 18: Recurrent Neural Networks (RNNs)


 Architecture of an RNN
 Unfolding an RNN
 Backpropagation Through Time
 Long Short-Term Memory (LSTM) Units
 Gated Recurrent Units (GRUs)
 Bidirectional RNNs
 Deep RNNs

Module 19: Generative Adversarial Networks (GANs)


 Structure of GAN
 Types of GAN Models
 Applications of GAN Models

Module 20: Transformers


 Attention Mechanism
 Transformer Architecture
 BERT (Bidirectional Encoder Representations from Transformers)
 VILBERT
 GPT (Generative Pre-trained Transformer)
 Applications of Transformer Models

Module 21: Applications of Generative AI


 Applications of Gen AI in Different Domains
 Examples of Prompt Engineering
 Fine-Tuning
 API Creation and Integration

Module 22: Reinforcement Learning


 Markov Decision Processes (MDPs)
 Q-Learning and Deep Q Networks (DQN)
 Actor-Critic Models
 Exploration vs. Exploitation Strategies

Module 23: Deployment of MLOps


 Ethical Considerations (Banking, E-commerce Sectors)
 Pushing Code to Repository
 Responsible AI
 Explainable AI
 Registry, Model & Data Monitoring

Module 24: Cloud Deployment


 Understanding Cloud Infrastructure Essentials
 Cloud-Based ML Services and Databases
 Containerization
 Cloud Enablement – Scalability and Flexibility
 Emerging Themes: FaaS, Edge Computing
 Federated Learning
 AutoML
 Explainable AI
 Cloud ML-Ops
 Deployment on Gemma Models on Vertex AI and Kubernetes Engine
 Scaling Using AWS

Module 25: Capstone Project


 A comprehensive, real-world assignment where participants apply their knowledge and
skills to solve industry-specific problems
 Integration of concepts from coursework, encouraging critical thinking and innovation
 Hands-on experience to become industry-ready by tackling complex challenges in a
professional setting

You might also like