Machine Learning Essentials Learning Plan

MLE1: Introduction to Machine Learning

• An Overview of Machine Learning
  • Humans in Machine Learning
  • What Happens in Machine Learning?
  • What is Machine Learning?
  • Types of Machine Learning
    • Supervised Learning
    • Unsupervised Learning
    • Reinforcement Learning
  • Machine Learning Styles
  • Machine Learning Algorithms (Sample)
  • Machine Learning Process
  • Technology Revolutions
  • Underfitting & Overfitting
  • Machine Learning Output Types
• Supervised Learning Algorithms
• Regression & Classification
• Decision Trees
• Unsupervised Learning Algorithms
• Clustering
• Association Rules (APRIORI)
• Reinforcement Learning Algorithms
• Model Testing and Validation
  • Model Validation Testing Top Tools
• Machine Learning Fundamentals – Progress Review

MLE2: Introduction to Statistical Learning Theory

• What is Statistical Learning Theory
• Decision Theory
• Sequence of Events
• Evaluating Decision Function
• Prediction Model Overview
  • Predictive Modeling
• Machine Learning Algorithms (Sample)
• Continuous Vs. Categorical Data
• Bias-Variance Tradeoff
• Typology of Errors
  • Approach 1: Least Squares
  • Approach 2: Nearest Neighbors
• Applications of Statistical Learning Theory
• Statistical Notation
• Types of Predictive Modeling
• Machine Learning Fundamentals – Progress Review

MLE3: Supervised Learning

• Decision Trees
  • Components of a Decision Tree
• Maximizing Information Gain
• Criterion for Attribute Selection
• The Gain Ratio
• GINI Index
• Ensemble Learning
• Random Forest
• Classification: K-Nearest Neighbors (KNN)
• Definition and Number of Neighbors
• Generalizability/Noise Tradeoff
• Euclidean Distance
• Normalization & Rescaling
• KNN & Categorical Values
  • KNN Process
  • Performance: AUROC Curve for KNN
• Machine Learning Fundamentals – Progress Review

MLE4: Unsupervised Learning

• Dimensionality Reduction
  • Johnson-Lindenstraum Lemma
  • Why Dimensionality Reduction?
  • Feature Selection
  • Feature Extraction
• PCA
• Auto-Encoders
• Clustering
  • Types of Clustering
  • K-Means Clustering
  • Hartigan-Wong Algorithm
• Complexity/Variety Tradeoff
• Applications
• Important Linkages
• Cluster Validation
• Hard Vs. Soft Clustering
• Optimal Number of Clusters (Elbow Method)
• Gaussian Mixture Models
  • Gaussian Mixed Models
  • Strengths of Gaussian Mixed Models
• Apriori Algorithms
• Rules in Data Mining
  • Confidence & Coverage
  • Lift
  • Finding Exploitable Rules
  • Finding Rules in Apriori
• Machine Learning Fundamentals – Progress Review

MLE5: Deep Learning

• What is Deep Learning?
  • History of Deep Learning
  • How Does Deep Learning Work?
• Neural Networks
  • Shallow Vs. Deep Neural Networks (Diagram 1)
  • Biological Neural Network (BNN)
  • Artificial Neural Network (ANN)
  • Comparison Between BNN and ANN
• Components of Neural Networks
  • Artificial Neural Network Concepts
  • Foundation of Neural Networks
• Perceptron Learning Process
• Backpropagation in Neural Networks
• Neural Network Activation Functions
• Role of the Activation Function
  • How Do They Work?
• How Do You Train an Algorithm?
• What Kinds of Neural Networks Exist?
• Neural Network Architecture
  • Convolutional Neural Networks (CNN)
  • CAPSNet
  • Recurrent Neural Networks (RNN)
  • Generative Adversarial Networks (GAN)
• What Kind of Problems Do NNS Solve?
• When to Use Deep Learning?
  • How to Create and Train Deep Learning Models
  • Programming Languages Used for Deep Learning
  • Top 5 Deep Learning Frameworks
  • Applications of Deep Learning (Diagram 2)
  • Business Applications
• Key Experiments in Deep Learning
• Business Applications of Neural Networks
• ANN Structure & Functioning
• Deep Neural Networks
• Artificial Neurons (Perceptions)
• Convolutional Neural Networks
  • Convolution Operation with 3X3X3 K
  • ReLu and Leaky ReLu Activation Functions
  • Why Convolutional Neural Networks?
• The Lottery Ticket Hypothesis (Diagram 3 & 4)
• Deep Double Descent (Diagram 5)
• Why Deep Neural Networks?
• Deep Learning Frameworks & Algorithms
• Machine Learning Fundamentals – Progress Review

MLE6: Business Applications of Machine Learning

• Natural Language Processing (NLP)
  • Top Advantages of Natural Language Processing
  • NLP Application
  • How Does Natural Language Processing Work?
  • Natural Language Processing (NLP) Tasks & Techniques
  • NLP Techniques
• Tokenization
• Parts of Speech Tagging
• Lemmatization and Stemming
• Stopword Removal
• Most Common and Powerful Uses of Natural Language Processing in Everyday Life
• NLP Applications
  • NLP Example: Speech Recognition
  • NLP Example: Chatbot
  • NLP Example: Sentiment Analysis
• Soft Clustering: Search Engine Indexing
• Clustering Example: Image Indexing
  • Clustering Example: Face Tagging
  • Clustering Example: Market Segmentation
  • Clustering Example: Advertising
  • Clustering Example: Recommendation Engines
• Classification Example: Disease Prediction
  • Classification Example: Fraud Detection
• Regression Example: Predictive Analytics
  • Regression Example: Product Propensity
  • Regression Example: Financial Forecasting
• Predictive Analytics: Security
  • Predictive Analysis: Uber Demand
  • Predictive Analysis: Churn Prevention
• Dimensionality Reduction
• Machine Learning Applications Across Industries (Diagram 1)
• Terminology
• Dependency Parsing
• Constituency Parsing
• Machine Learning Fundamentals – Progress Review