MACHINE LEARNING PROGRAM

Overview:

It is the science of getting computers to operate without being explicitly programmed, which is called machine learning. We now have self-driving vehicles, realistic voice recognition, efficient online search, and a better grasp of the human genome thanks to advances in machine learning over the last decade. There’s a good chance you’re using machine learning every day without even realising it. The best strategy to develop towards human-level artificial intelligence, in the opinion of many academics, is to use this method. Machine learning techniques will be covered in this course, as well as how to use them effectively in your own work, so don’t be afraid to experiment! Aside from the theoretical basis of learning, you’ll learn to use these approaches swiftly and powerfully in new situations as well. On the final day you’ll learn about some of Silicon Valley’s most successful innovation strategies in machine learning and AI.

Machine learning, data mining, and statistical pattern identification are covered in depth in this course. topics include:

1) Supervised and unsupervised learning, as well as kernels and neural networks.

2) Learning without supervision (clustering, dimensionality reduction, recommender systems, deep learning).

3) Best practises in machine learning, including bias/variance theory and innovation in machine learning and artificial intelligence.

Learning algorithms may be used to develop smart robots (perception, control), online search (anti-spam), medical informatics (audio, database mining), and other domains. The course will also draw from various case studies and applications.

Key Learnings:

  • Understand supervised and unsupervised learning, recommendation engines, and time series modelling techniques.
  • Through a hands-on approach that involves working on four large end-to-end projects and 25+ hands-on exercises, you’ll gain practical mastery of the ideas, methods, and applications of machine learning.
  • Acquire a deep understanding of machine learning’s statistical and heuristic elements.
  • Support vector machines, kernel SVM, naive Bayes, decision tree classifier, random forest classifier, logistic regression, K-means clustering, and more models may all be implemented in Python.
  • Decode multiple accuracy indicators and validate machine learning models.
  • Another set of optimization procedures, including boosting and bagging approaches, can be used to improve the final models.
  • Understand the theoretical ideas of machine learning and how they connect to the practical parts of the field.

Course Modules

  • Course Introduction
  • Learning Objectives
  • The emergence of Artificial Intelligence
  • Artificial Intelligence in Practice
  • Sci-Fi Movies with the concept of AI
  • Recommender Systems
  • Relationship Between Artificial Intelligence, Machine Learning, and Data Science – Part A
  • Relationship Between Artificial Intelligence, Machine Learning, and Data Science – Part B
  • Definition and Features of Machine Learning
  • Machine Learning Approaches
  • Machine Learning Techniques
  • Applications of Machine Learning – Part A
  • Applications of Machine Learning – Part B
  • Key Takeaways
  • Certification Details and Criteria:
  • 85 percent completion of online self-paced learning or attendance of one live virtual classroom
  • A score of at least 75 percent in the course-end assessment
  • Successful evaluation in at least one project
  • Learning Objectives
  • Data Exploration: Loading Files
  • Demo: Importing and Storing Data
  • Practice: Automobile Data Exploration I
  • Data Exploration Techniques: Part 1
  • Data Exploration Techniques: Part 2
  • Seaborn
  • Demo: Correlation Analysis
  • Practice: Automobile Data Exploration II
  • Data Wrangling
  • Missing Values in a Dataset
  • Outlier Values in a Dataset
  • Demo: Outlier and Missing Value Treatment
  • Practice: Data Exploration III
  • Data Manipulation
  • Functionalities of Data Object in Python: Part A
  • Functionalities of Data Object in Python: Part B
  • Different Types of Joins
  • Typecasting
  • Demo: Labor Hours Comparison
  • Practice: Data Manipulation
  • Key Takeaways
  • Lesson-end project: Storing Test Results
  • Learning Objectives
  • Supervised Learning
  • Supervised Learning- Real-Life Scenario
  • Understanding the Algorithm
  • Supervised Learning Flow
  • Types of Supervised Learning – Part A
  • Types of Supervised Learning – Part B
  • Types of Classification Algorithms
  • Types of Regression Algorithms – Part A
  • Regression Use Case
  • Accuracy Metrics
  • Cost Function
  • Evaluating Coefficients
  • Demo: Linear Regression
  • Practice: Boston Homes I
  • Challenges in Prediction
  • Types of Regression Algorithms – Part B
  • Demo: Bigmart
  • Practice: Boston Homes II
  • Logistic Regression – Part A
  • Logistic Regression – Part B
  • Sigmoid Probability
  • Accuracy Matrix
  • Demo: Survival of Titanic Passengers
  • Practice: Iris Species
  • Key Takeaways
  • Lesson-end Project: Health Insurance Cost
  • Learning Objectives
  • Feature Selection
  • Regression
  • Factor Analysis
  • Factor Analysis Process
  • Principal Component Analysis (PCA)
  • First Principal Component
  • Eigenvalues and PCA
  • Demo: Feature Reduction
  • Practice: PCA Transformation
  • Linear Discriminant Analysis
  • Maximum Separable Line
  • Find Maximum Separable Line
  • Demo: Labeled Feature Reduction
  • Practice: LDA Transformation
  • Key Takeaways
  • Lesson-end Project: Simplifying Cancer Treatment
  • Learning Objectives
  • Overview of Classification
  • Classification: A Supervised Learning Algorithm
  • Use Cases
  • Classification Algorithms
  • Decision Tree Classifier
  • Decision Tree: Examples
  • Decision Tree Formation
  • Choosing the Classifier
  • Overfitting of Decision Trees
  • Random Forest Classifier- Bagging and Bootstrapping
  • Decision Tree and Random Forest Classifier
  • Performance Measures: Confusion Matrix
  • Performance Measures: Cost Matrix
  • Demo: Horse Survival
  • Practice: Loan Risk Analysis
  • Naive Bayes Classifier
  • Steps to Calculate Posterior Probability: Part A
  • Steps to Calculate Posterior Probability: Part B
  • Support Vector Machines: Linear Separability
  • Support Vector Machines: Classification Margin
  • Linear SVM: Mathematical Representation
  • Non-linear SVMs
  • The Kernel Trick
  • Demo: Voice Classification
  • Practice: College Classification
  • Key Takeaways
  • Lesson-end Project: Classify Kinematic Data
  • Learning Objectives
  • Overview
  • Example and Applications of Unsupervised Learning
  • Clustering
  • Hierarchical Clustering
  • Hierarchical Clustering: Example
  • Demo: Clustering Animals
  • Practice: Customer Segmentation
  • K-means Clustering
  • Optimal Number of Clusters
  • Demo: Cluster-Based Incentivization
  • Practice: Image Segmentation
  • Key Takeaways
  • Lesson-end Project: Clustering Image Data
  • Learning Objectives
  • Overview of Time Series Modeling
  • Time Series Pattern Types Part A
  • Time Series Pattern Types Part B
  • White Noise
  • Stationarity
  • Removal of Non-Stationarity
  • Demo: Air Passengers I
  • Practice: Beer Production I
  • Time Series Models Part A
  • Time Series Models Part B
  • Time Series Models Part C
  • Steps in Time Series Forecasting
  • Demo: Air Passengers II
  • Practice: Beer Production II
  • Key Takeaways
  • Lesson-end Project: IMF Commodity Price Forecast
  • Learning Objectives
  • Overview
  • Ensemble Learning Methods Part A
  • Ensemble Learning Methods Part B
  • Working of AdaBoost
  • AdaBoost Algorithm and Flowchart
  • Gradient Boosting
  • XGBoost
  • XGBoost Parameters Part A
  • XGBoost Parameters Part B
  • Demo: Pima Indians Diabetes
  • Practice: Linearly Separable Species
  • Model Selection
  • Common Splitting Strategies
  • Demo: Cross-Validation
  • Practice: Model Selection
  • Key Takeaways
  • Lesson-end Project: Tuning Classifier Model with XGBoost
  • Learning Objectives
  • Introduction
  • Purposes of Recommender Systems
  • Paradigms of Recommender Systems
  • Collaborative Filtering Part A
  • Collaborative Filtering Part B
  • Association Rule Mining
  • Association Rule Mining: Market Basket Analysis
  • Association Rule Generation: Apriori Algorithm
  • Apriori Algorithm Example: Part A
  • Apriori Algorithm Example: Part B
  • Apriori Algorithm: Rule Selection
  • Demo: User-Movie Recommendation Model
  • Practice: Movie-Movie recommendation
  • Key Takeaways
  • Lesson-end Project: Book Rental Recommendation
  • Learning Objectives
  • Overview of Text Mining
  • Significance of Text Mining
  • Applications of Text Mining
  • Natural Language Toolkit Library
  • Text Extraction and Preprocessing: Tokenization
  • Text Extraction and Preprocessing: N-grams
  • Text Extraction and Preprocessing: Stop Word Removal
  • Text Extraction and Preprocessing: Stemming
  • Text Extraction and Preprocessing: Lemmatization
  • Text Extraction and Preprocessing: POS Tagging
  • Text Extraction and Preprocessing: Named Entity Recognition
  • NLP Process Workflow
  • Demo: Processing Brown Corpus
  • Practice: Wiki Corpus
  • Structuring Sentences: Syntax
  • Rendering Syntax Trees
  • Structuring Sentences: Chunking and Chunk Parsing
  • NP and VP Chunk and Parser
  • Structuring Sentences: Chinking
  • Context-Free Grammar (CFG)
  • Demo: Twitter Sentiments
  • Practice: Airline Sentiment
  • Key Takeaways