DI04000061 · Semester 4 · 5G scheme
Introduction Machine Learning
Notes and solutions following the Gujarat Technological University (GTU) syllabus for DI04000061. Independent material — not issued by the university.
Computer EngineeringComputer Science & Engineering
Materials
Complete Book
The whole syllabus, unit by unit, written for the exam.
Complete Book
122 pages
Premium Preview · 14 pages
PYQ Solutions
Past university papers, fully solved.
Solved past papers — detailed answers
28 pages · English + ગુજરાતી
Premium Preview · 4 pages
Syllabus units
Unit 1: Introduction to Machine Learning
- Overview of Human Learning and Machine Learning
- Types of Machine Learning: Supervised, Unsupervised, Reinforcement
- Benefits Machine Learning
- Challenges of Machine Learning
- Applications of Machine Learning
- Tools and Technology for Machine Learning
Unit 2: Python libraries for Machine Learning
- Numpy
- Creating and Accessing Array: array(), zeros(), ones(), arange(), reshape()
- Stacking & Splitting: stack(), split()
- Maths Functions: add(), subtract(), multiply(), divide(), power(), sqrt()
- Statistics Functions: mean(), median(), std(), var()
- Pandas
- Data structure: Series(), DataFrame()
- Manipulating Data: isnull(), sum(), min(), max() drop(), dropna(), duplicated() , loc[], head(), tail(), shape, columns, sort_values()
- Working with CSV File: read_csv(), to_csv()
- Matplotlib
- Functions: plot(), scatter(), bar(), hist(), boxplot() , pie(), title(), xlabel(), ylabel(), grid(), show(), savefig()
- Scikit-learn
- Key concepts and features
- Functions: load_*(), train_test_split()
Unit 3: Preparing to Model and Evaluation
- Machine Learning activities
- Types of data in Machine Learning: Numerical (quantitative) data, Categorical (qualitative) data
- Data quality and remediation
- Data Pre-Processing: Dimensionality reduction, Feature subset selection
- Selecting a Model: Predictive/Descriptive
- Training a Model for supervised learning: Holdout method, K-fold Cross-validation method
- Performance Evaluation of a model: confusion matrix
- Improving Performance of a model
Unit 4: Supervised Machine Learning
- Introduction to Supervised Learning
- Brief explanation of Supervised Machine Learning
- Learning Steps in Supervised Machine Learning
- Real world Applications/Examples of Supervised Machine Learning
- Advantage and disadvantage of Supervised Machine Learning
- Classification
- Define Classification
- Types of classification: Binary, Multi-class
- k-Nearest Neighbor (kNN): Working of k-NN, Need of k-NN algorithm, Select value of k, advantage and disadvantage of k-NN algorithm
- Support Vector Machines: Fundamentals concept
- Regression
- Define Regression analysis
- List types of Regression
- Linear regression: List types of Linear Regression, mathematical equation of linear regression, diagram of linear regression line (positive, negative)
- Simple linear regression: Description, objective
- List real-world examples of regression analysis
Unit 5: Unsupervised Machine Learning and Generative AI
- Introduction of Unsupervised Learning
- Need of unsupervised learning
- Working of unsupervised learning
- Types of unsupervised learning: Clustering, Association rules
- Real-world examples of unsupervised Learning
- Supervised vs. Unsupervised Learning
- Generative AI
- Define Generative AI
- Working of Generative AI
- Applications of Generative AI
- Case Study: Simulate port-wide hydrogen adoption, and forecast emission reductions with Generative AI and Green Hydrogen.
About this course
Study materials, question papers, and solutions for Introduction Machine Learning (DI04000061) - Computer Engineering, Semester 4