Artificial Intelligence – AI 6 Projects Course

This hands-on course dives into the world of Artificial Intelligence through project-based learning. Covering foundational AI concepts, machine learning algorithms, and deep learning applications, students will work on six diverse projects that apply AI in practical, real-world scenarios. By the end of the course, students will have a strong portfolio showcasing their AI skills.

What you’ll learn

Deploy Emotion AI-based model using Tensorflow 2.0 Serving and use the model to make inferences.
Understand the concept of Explainable AI and uncover the black nature of Artificial Neural Networks and visualize their hidden layers using the GradCam technique
Develop a Deep Learning model to automate and optimize the brain tumor detection processes at a hospital.
Build and train AI model to detect and localize brain tumors using ResNets and ResUnet networks (Healthcare applications).
Understand the theory and intuition behind Segmentation models and state-of-the-art ResUnet networks.
Build, train, deploy AI models in business to predict customer default on credit cards using AWS SageMaker XGBoost algorithm.
Optimize XGBoost model parameters using hyperparameters optimization search.
Apply AI in business applications by performing customer market segmentation to optimize marketing strategy.
Understand the underlying theory and mathematics behind the DeepDream algorithm for Art generation.
Develop, train, and test State-of-the art DeepDream algorithm to create AI-based art masterpieces using Keras API in TF 2.0.
Develop ANN models and train them in Google Colab while leveraging the power of GPUs and TPUs.

Course Content:

Module 1: Introduction to AI:

Overview of Artificial Intelligence, Machine Learning (ML), and Deep Learning (DL)
Real-world AI applications and trends

Module2: Emotional AI

Task #1 – Understand the Problem Statement & Business Case
Task #2 – Import Libraries and Datasets
Task #3 – Perform Image Visualization
Task #4 – Perform Images Augmentation
Task #5 – Perform Data Normalization and Scaling
Task #6 – Understand Artificial Neural Networks (ANNs) Theory & Intuition
Task #7 – Understand ANNs Training & Gradient Descent Algorithm
Task #8 – Understand Convolutional Neural Networks and ResNets
Task #9 – Build ResNet to Detect Key Facial Points
Task #10 – Compile and Train Facial Key Points Detector Model
Task #11 – Assess Trained ResNet Model Performance
Task #12 – Import and Explore Facial Expressions (Emotions) Datasets
Task #13 – Visualize Images for Facial Expression Detection
Task #14 – Perform Image Augmentation
Task #15 – Build & Train a Facial Expression Classifier Model
Task #16 – Understand Classifiers Key Performance Indicators (KPIs)\
Task #17 – Assess Facial Expression Classifier Model
Task #18 – Make Predictions from Both Models: 1. Key Facial Points & 2. Emotion
Task #19 – Save Trained Model for Deployment
Task #20 – Serve Trained Model in TensorFlow 2.0 Serving
Task #21 – Deploy Both Models and Make Inference

Module3: AI in HealthCare

Task #1 – Understand the Problem Statement and Business Case
Task #2 – Import Libraries and Datasets
Task #3 – Visualize and Explore Datasets
Task #4 – Understand the Intuition behind ResNet and CNNs
Task #5 – Understand Theory and Intuition Behind Transfer Learning
Task #6 – Train a Classifier Model To Detect Brain Tumor
Task #7 – Assess Trained Classifier Model Performance
Task #8 – Understand ResUnet Segmentation Models Intuition
Task #9 – Build a Segmentation Model to Localize Brain Tumors
Task #10 – Train ResUnet Segmentation Mod
Task #11 – Assess Trained ResUNet Segmentation Model Performance

Module4: AI In Business Marketing

Task #1 – Understand AI Applications in Marketing
Task #2 – Import Libraries and Datasets
Task #3 – Perform Exploratory Data Analysis (Part #1)
Task #4 – Perform Exploratory Data Analysis (Part #2)
Task #5 – Understand Theory and Intuition Behind K-Means Clustering Algorit
Task #6 – Apply the Elbow Method to Find the Optimal Number of Cluster
Task #7 – Apply K-Means Clustering Algorithm
Task #8 – Understand Intuition Behind Principal Component Analysis (PCA
Task #9 – Understand the Theory and Intuition Behind Auto-encoders
Task #10 – Apply Auto-encoders and Perform Clustering

Module5: AI In Business (Finance) AutoML

Notes on Amazon Web Services (AWS
Task #1 – Understand the Problem Statement & Business Case
Task #2 – Import Libraries and Datasets
Task #3 – Visualize and Explore Dataset
Task #4 – Clean Up the Data
Task #5 – Understand the Theory & Intuition Behind XG-Boost Algorithm
Task #6 – Understand XG-Boost Algorithm Key Steps
Task #7 – Train XG-Boost Algorithm Using Scikit-Learn
Task #8 – Perform Grid Search and Hyper-parameters Optimization
Task #9 – Understand XG-Boost in AWS SageMaker
Task #10 – Train XG-Boost in AWS SageMaker
Task #11 – Deploy Model and Make Inference
Task #12 – Train and Deploy Model Using AWS AutoPilot (Minimal Coding Required!)

Module6: Creative AI

Task #1 – Understand the Problem Statement & Business Case
Task #2 – Import Model with Pre-trained Weights
Task #3 – Import and Merge Images
Task #4 – Run the Pre-trained Model and Explore the Activation
Task #5 – Understand the Theory & Intuition Behind Deep Dream Algorithm
Task #6 – Understand The Gradient Operations in TF 2.0
Task #7 – Implement Deep Dream Algorithm Part #1
Task #8 – Implement Deep Dream Algorithm Part #2
Task #9 – Apply DeepDream Algorithm to Generate Image
Task #10 – Generate DeepDream Video

Module7: Explainable AI With Zero Coding

Explainable AI Dataset Download & Link to DataRobot
Project Overview on Food Recognition with A
DataRobot Demo 1 – Upload and Explore Datase
DataRobot Demo 2 – Train AI/ML Model
DataRobot Demo 3 – Explainable AI

Module8: Crash Course on AWS, S3, SageMaker

What is AWS and Cloud Computing
Key Machine Learning Components and AWS Tou
Regions and Availability Zone
Amazon S3
EC2 and Identity and Access Management (IAM)
AWS Free Tier Account Setup and Overview
AWS SageMaker Overview
AWS SageMaker Walk-through
AWS SageMaker Studio Overview
AWS SageMaker Studio Walk-through
AWS SageMaker Model Deployment

Who this course is for:

Seasoned consultants wanting to transform industries by leveraging AI.
AI Practitioners want to advance their careers and build their portfolio.
Visionary business owners who want to harness the power of AI to maximize revenue, reduce costs, and optimize their business.
Visionary business owners who want to harness the power of AI to maximize revenue, reduce costs, and optimize their business.

CareerPath:

After completing this course, students will be well-prepared for various entry-level to intermediate roles in artificial intelligence and machine learning, such as: