Modern Artificial Intelligence Masterclass: Build 6 Projects

Modern Artificial Intelligence Masterclass: Build 6 Projects

English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 15 Hours | 9.61 GB

Harness the power of AI to solve practical, real-world problems in Finance, Tech, Art and Healthcare

AI is the science that empowers computers to mimic human intelligence such as decision making, reasoning, text processing, and visual perception. AI is a broader general field that entails several sub-fields such as machine learning, robotics, and computer vision.

For companies to become competitive and skyrocket their growth, they need to leverage AI power to improve processes, reduce cost and increase revenue. AI is broadly implemented in many sectors nowadays and has been transforming every industry from banking to healthcare, transportation and technology.

The demand for AI talent has exponentially increased in recent years and it’s no longer limited to Silicon Valley! According to Forbes, AI Skills are among the most in-demand for 2020.

The purpose of this course is to provide you with knowledge of key aspects of modern Artificial Intelligence applications in a practical, easy and fun way. The course provides students with practical hands-on experience using real-world datasets. The course covers many new topics and applications such as Emotion AI, Explainable AI, Creative AI, and applications of AI in Healthcare, Business, and Finance.

One key unique feature of this course is that we will be training and deploying models using Tensorflow 2.0 and AWS SageMaker. In addition, we will cover various elements of the AI/ML workflow covering model building, training, hyper-parameters tuning, and deployment. Furthermore, the course has been carefully designed to cover key aspects of AI such as Machine learning, deep learning, and computer vision.

Here’s a summary of the projects that we will be covering:

  • Project #1 (Emotion AI): Emotion Classification and Key Facial Points Detection Using AI
  • Project #2 (AI in HealthCare): Brain Tumor Detection and Localization Using AI
  • Project #3 (AI in Business/Marketing): Mall Customer Segmentation Using Autoencoders and Unsupervised Machine Learning Algorithms
  • Project #4: (AI in Business/Finance): Credit Card Default Prediction Using AWS SageMaker’s XG-Boost Algorithm (AutoPilot)
  • Project #5 (Creative AI): Artwork Generation by AI
  • Project #6 (Explainable AI): Uncover the Blackbox nature of AI and Visualize hidden layers using GradCam
Table of Contents

Introduction
1 Introduction and Welcome Message
2 Introduction, Key Tips and Best Practices
3 Course Outline and Key Learning Outcomes
4 Get the Materials

Bonus Materials (Download now!)
5 Link to Bonus Materials

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

AI in Healthcare
28 Project Introduction and Welcome Message
29 Task #1 – Understand the Problem Statement and Business Case
30 Task #2 – Import Libraries and Datasets
31 Task #3 – Visualize and Explore Datasets
32 Task #4 – Understand the Intuition behind ResNet and CNNs
33 Task #5 – Understand Theory and Intuition Behind Transfer Learning
34 Task #6 – Train a Classifier Model To Detect Brain Tumors
35 Task #7 – Assess Trained Classifier Model Performance
36 Task #8 – Understand ResUnet Segmentation Models Intuition
37 Task #9 – Build a Segmentation Model to Localize Brain Tumors
38 Task #10 – Train ResUnet Segmentation Model
39 Task #11 – Assess Trained ResUNet Segmentation Model Performance

AI in Business (Marketing)
40 Project Introduction and Welcome Message
41 Task #1 – Understand AI Applications in Marketing
42 Task #2 – Import Libraries and Datasets
43 Task #3 – Perform Exploratory Data Analysis (Part #1)
44 Task #4 – Perform Exploratory Data Analysis (Part #2)
45 Task #5 – Understand Theory and Intuition Behind K-Means Clustering Algorithm
46 Apply Elbow Method to Find the Optimal Number of Clusters
47 Task #7 – Apply K-Means Clustering Algorithm
48 Task #8 – Understand Intuition Behind Principal Component Analysis (PCA)
49 Task #9 – Understand the Theory and Intuition Behind Auto-encoders
50 Task #10 – Apply Auto-encoders and Perform Clustering

AI In Business (Finance) & AutoML
51 Project Introduction and Welcome Message
52 Notes on Amazon Web Services (AWS)
53 Task #1 – Understand the Problem Statement & Business Case
54 Task #2 – Import Libraries and Datasets
55 Task #3 – Visualize and Explore Dataset
56 Task #4 – Clean Up the Data
57 Task #5 – Understand the Theory & Intuition Behind XG-Boost Algorithm
58 Task #6 – Understand XG-Boost Algorithm Key Steps
59 Task #7 – Train XG-Boost Algorithm Using Scikit-Learn
60 Task #8 – Perform Grid Search and Hyper-parameters Optimization
61 Task #9 – Understand XG-Boost in AWS SageMaker
62 Task #10 – Train XG-Boost in AWS SageMaker
63 Task #11 – Deploy Model and Make Inference
64 Task #12 – Train and Deploy Model Using AWS AutoPilot (Minimal Coding Required!)

Creative AI
65 Project Introduction and Welcome Message
66 Task #1 – Understand the Problem Statement & Business Case
67 Task #2 – Import Model with Pre-trained Weights
68 Task #3 – Import and Merge Images
69 Task #4 – Run the Pre-trained Model and Explore Activations
70 Task #5 – Understand the Theory & Intuition Behind Deep Dream Algorithm
71 Task #6 – Understand The Gradient Operations in TF 2.0
72 Task #7 – Implement Deep Dream Algorithm Part #1
73 Task #8 – Implement Deep Dream Algorithm Part #2
74 Task #9 – Apply DeepDream Algorithm to Generate Images
75 Task #10 – Generate DeepDream Video

Explainable AI
76 Project Introduction and Welcome Message
77 Introduction and Welcome Message

Crash Course on AWS, S3, and SageMaker
78 What is AWS and Cloud Computing
79 Key Machine Learning Components and AWS Tour
80 Regions and Availability Zones
81 Amazon S3
82 EC2 and Identity and Access Management (IAM)
83 AWS Free Tier Account Setup and Overview
84 AWS SageMaker Overview
85 AWS SageMaker Walk-through
86 AWS SageMaker Studio Overview
87 AWS SageMaker Studio Walk-through
88 AWS SageMaker Model Deployment