Introduction to Machine Learning Notes
Subject Overview
The second course in the AI/
Subject at a glance
2
Units
26
Topics
2
Credits
2
Infographics
Unit-wise Syllabus
2 units — open any unit for detailed topic-wise notes, diagrams and important exam questions
- Definition
- history and applications of machine learning
- types of ML (supervised, unsupervised, semi-supervised, reinforcement)
- labeled/unlabeled datasets
- regression vs classification
- training/validation/testing framework
- performance metrics — confusion matrix
- accuracy
- precision
- recall
- F1 score
- AUC
- Accuracy
- (TP + TN) / total
- Precision
- TP / (TP + FP): how many predicted positives were right
- Recall
- TP / (TP + FN): how many actual positives were found
- F1 score
- Harmonic mean of precision and recall
Study guide
Machine learning lets computers learn patterns from data instead of following fixed rules. You study its definition, history and applications, the types (supervised, unsupervised, semi-supervised, reinforcement), labelled and unlabelled data, regression versus classification, the training, validation and test framework, and performance metrics: confusion matrix, accuracy, precision, recall, F1 score and AUC. Learn precision and recall with a medical-test example; it makes the trade-off clear.
- Linear and non-linear regression
- logistic regression
- Naive Bayes
- K-Nearest Neighbors
- decision trees
- introduction to artificial neural networks
- perceptron learning algorithm
- single-layer perceptron
- introduction to SVM for linearly separable data
- K-Means
- hierarchical clustering
- DBSCAN
- clustering validation measures
- ethical considerations and real-world applications of ML
Regression
Linear and non-linear regression
Classification
Logistic regression, Naive Bayes, KNN, decision trees
Neural networks
Perceptron, SVM basics
Clustering
K-Means, hierarchical, DBSCAN
Study guide
This unit covers the main algorithms: linear and non-linear regression, logistic regression, Naive Bayes, K-nearest neighbours, decision trees, artificial neural networks with the perceptron learning algorithm, an introduction to SVM for linearly separable data, and unsupervised methods: K-Means, hierarchical clustering, DBSCAN and cluster validation, along with ethical considerations. For every algorithm, note what problem it solves, how it learns and its main weakness.
Why Introduction to Machine Learning Matters
Machine learning powers recommendation systems, fraud detection, language tools and much more, and it is one of the highest-demand skill areas worldwide. This paper is your entry point to data science and AI careers.
How to Prepare for Introduction to Machine Learning
- Understand accuracy, precision, recall and F1 with a confusion matrix example.
- Practise each algorithm on a small data set in Python.
- Learn the difference between overfitting and underfitting.
- Keep a one-page summary of when to use each algorithm.
Introduction to Machine Learning: Frequently Asked Questions
What is the difference between supervised and unsupervised learning?
Supervised learning learns from labelled examples to predict outputs, while unsupervised learning finds structure such as clusters in unlabelled data.
What is overfitting?
Overfitting happens when a model learns the training data too closely, including noise, and then performs poorly on new data.