Artificial Intelligence

Curriculum

This Artificial Intelligence course offers a comprehensive curriculum that covers foundational and advanced AI concepts. Students will explore Python programming, machine learning techniques, data science analysis, and deep learning applications. The course delves into practical topics like recommendation systems, natural language processing, and time series analysis, alongside real-time projects and hands-on experience. Additionally, learners will gain skills in web development using Django, AI deployment on the cloud, and building AI-powered applications using ChatGPT API. This curriculum prepares students to excel in AI, machine learning, and data science industries.

Overview

This AI course provides a solid foundation in artificial intelligence, machine learning, and data science. It covers Python programming, key machine learning algorithms, deep learning, and natural language processing, with hands-on experience using tools like TensorFlow and Scikit-learn. The course includes practical projects in AI applications such as recommendation systems, chatbots, and time series analysis. Additionally, it covers web development with Django and cloud deployment, preparing students to apply AI in real-world scenarios across various industries.

Modules

Python Module

Module 1: Python

Python Crash Course

Python Tools
Anaconda Software Installation
Python Basics
Assignment Operators
Control Structures
Oops – Functions and Class
List, Tuple
Python Libraries: Numpy, Pandas, Scikit-learn, Matplotlib, Seaborn, Opencv, Tensorflow, Keras, NLTK, Spacy, Pytorch

Module 2: ML-Regression

Problem Identification in AI
Supervised Learning
Unsupervised Learning
Semisupervised Learning
Scenario-based AI Problems with Solutions
Simple Linear Regression
Model Creation
Deployment Phase
Evaluation Metric
Multiple Linear Regression
Support Vector Machine
Decision Tree
Random Forest
Boosting Algorithms
Cross Validation – Gridsearch
Evaluating Regression Models Performance

Module 3: ML-Classification

Confusion Matrix
Classification Algorithms
Logistic Regression
Naive Bayes
K-Nearest Neighbor (K-NN)
Support Vector Machine (SVM)
Kernel SVM
Decision Tree Classification
Random Forest Classification
Evaluating Classification Model Performance

Module 4: ML-Clustering

How to create Virtual Environment?
K-Means Clustering
Agglomerative Clustering
Hierarchical Clustering
Affinity Propagation
Mean Shift Clustering
Spectral Clustering
Optics Clustering
Birch Clustering

Module 5: Advanced ML-Feature Selection

Feature Selection
Select-K Algorithm
RFE
Advanced ML Flow

Module 6: Advanced ML-Dimensionality Reduction

Scalar and Vector
Principle Component Analysis
LDA
Advanced Techniques- Fitting methods
Overfitting, Underfitting and Best fitting

Module 7: DS-Univariate Analysis

Data Science Introduction
Loading Data set
Missing Data
Categorical Data
Splitting Data set
Feature Scaling
Quantitative and Qualitative
Central Tendency
Percentile
IQR
Outliers
Histogram, Skewness, Kurtosis
Data Preprocessing
Variance and Standard Deviation
Normal Distribution
Probability Density Function
Z-Score

Module 8: DS-Bivariate Analysis

Co-variance and Correlation
Multicolinearity
VIF
T-Test
Hypothesis Testing
ANAVO

Module 9: DS-Data Visualization

Scatter plot
Bar chart
Pie chart
Histogram
Line Plot
Area Plot
Box Plot
Violin Plot

Module 10: Web Development using Django

Web Development Demo
Create Project and App
HTML page
Backend view
Output page

Module 11: Recommendation System

User based recommendation
Item based recommendation
Content based recommendation
Popularity based recommendation
Uplift Modelling – How e-commerce sends offer mail to you
Customer Life Time Value – Which customer stays longerg

Module 12: Deep Learning

Introduction to DL
How Neural Network works?
Gradient Descent
Backpropagation
ANN
CNN
Pre-trained models
Transfer Learning
Real Time Project with hands-on
LSTM
RNN
Hands-on: (Opencv, Keras and Tensorflow Library)
Secure Face Recognition online payment using Deep Learning
Haemorrhage prediction using Deep Learning
Object Detection using Tensorflow Deep Learning Framework
Image Generator using GAN

Module 13: Time Series Analysis

Intro to Time Series
Visualizing a Time Series
Patterns in a Time Series
Stationary and non-stationary Time Series
How to make a Time Series stationary?
How to test for stationarity?
Share Market Analysis
Components in Time Series
Non-Stationarity Series
EDA- Stock Data
Stationarity – Hypothesis
Auto Correlation
Partial Auto Correlation
Auto regression
Forecasting
Moving Average
ARMA
ARIMA
SARIMA
VAR
Advanced time series algorithms

Module 14: NLP

NLP Introduction
TF-IDF Vectorization
Sentimental Analysis
Text Preprocessing
Topic Modelling
Stop Words
Tokenization
Stemming and Lemmatization
Bag of Words
Model Word Vectorizer
TF-IDF
POS Tagging
Named Entity Recognition
Word Cloud
Libraries: NLTK, Spacy

Module 15: Prompt Engineering, LLM

What is API?
ChatGPT API Introduction
OpenAI API and Level 1 code
LLM Introduction
ChatGPT prompt
Chatbot model customized ChatGPT
Create end user ChatGPT with sharable link
Building Systems with ChatGPT API
Introduction BSWC Problem Statement
BSWC- Classify the inputs
BSWC- Moderation
BSWC- Chaining Prompting
BSWC- Chain prompting-2
BSWC- Chainprompting Continuation
BSWC-Check Outputs
BSWC- End to End System
BSWC- Evaluate-1
BSWC- Evaluate-2

Module 16: Real-time Application with ChatGPT API

Realtime Implementation Website Demo
Overview flow of Realtime Application
Integrate ChatGPT API with Live website to create chatbot
Website-AI Chatbot

Module 17: GenAl-Advanced Techniques

GAN
Transformers
RAG
Self attention Mechanism
Stable Diffusion
Auto Encoders
Variational Encoders
Conversational Al
Hugging Face
Llamaindex
Llama-2
LangChain
Gemini Al API

Module 18: Deployment on Cloud Platform

Deployment Cloud Procedures
Deployment on GCP App Engine Serverless Procedure
Deployment GCP through Docker
Deployment GCP through Kubernetes

AI Projects

Project 1: AI in Finance
Project 2: AI in Healthcare
Project 3: AI in Marketing
Project 4: AI in Online Platforms
Project 5: Face Mask Detection
Project 6: Object Detection Project
Project 7: Stock Market Analysis
Project 8: AQI
Project 9: Fake News Detection
Project 10: WhatsApp Chat Analysis
Project 11: ChatBot Creation
Project 12: Gen AI Project

Hands-On Learning Opportunities

This AI course provides hands-on learning through practical projects, including AI applications in finance, healthcare, and marketing. Students will work with machine learning algorithms, deep learning models, and AI-powered web development, including chatbots and recommendation systems. The course also covers deploying AI models on cloud platforms, ensuring learners gain real-world experience to excel in the AI field.

Who Should Enroll?

This course is ideal for:

- Aspiring AI professionals looking to build a career in artificial intelligence.
- Data scientists seeking to expand their knowledge in AI and machine learning.
- Software developers interested in integrating AI into their projects.
- Individuals with a basic understanding of Python programming who want to deepen their skills.
- Beginners eager to enter the AI field with no prior experience.
- Professionals aiming to upskill and stay competitive in the rapidly evolving AI industry.

Why Choose This Course?

This course offers a comprehensive curriculum covering AI, machine learning, and deep learning, with hands-on experience through real-world projects. You’ll learn from expert instructors and gain practical skills in deploying AI models and building AI-powered systems. Whether you’re looking to start your AI career or upskill, this course prepares you for in-demand roles in the rapidly growing AI industry.

Start Your Artificial Intelligence Journey Today

Begin your AI learning journey with hands-on projects and expert guidance. Equip yourself with the skills needed to thrive in the AI industry and open doors to exciting career opportunities. Start today!