Semester 5Year 3 · OddCore Subject★★★★★ Hard
CS 501

Machine Learning

Study of ML algorithms, supervised/unsupervised learning, neural networks, and deep learning fundamentals.

4Units
25Topics
4Credits
60hLecture hrs
100Max marks
Your Progress
0 / 25 topics
0% complete
Overview
🎯
Why it matters
ML is THE future. ChatGPT, recommendation systems, fraud detection, self-driving cars — all ML. This is the most in-demand skill in tech. Master this, earn ₹30-50 LPA at AI startups.
💼
Placement relevance
HIGHEST demand field. ML Engineer roles at Google, Microsoft, Amazon. Data Scientist positions everywhere. Kaggle competitions boost resume. Every product company wants ML talent.
🔗
Prerequisites for
Deep Learning · Natural Language Processing · Computer Vision · AI Research · Data Science · Reinforcement Learning
📚
Recommended books
Pattern Recognition and Machine Learning by Christopher Bishop · Hands-On Machine Learning by Aurélien Géron · Deep Learning by Goodfellow, Bengio, and Courville · Machine Learning by Tom Mitchell
Curriculum — 4 Units
U1
Unit 1 · 7 Topics · 0% complete
Supervised Learning
⚡ Key Formulae
Linear Regression:y = mx + c; Cost = (1/2m)Σ(h(x)-y)²
Gradient Descent:θ := θ - α(∂J/∂θ)
Sigmoid:σ(z) = 1/(1 + e^(-z))
Linear Regression
Logistic Regression
Decision Trees
Random Forest
SVM
Naive Bayes
KNN
U2
Unit 2 · 6 Topics · 0% complete
Unsupervised Learning
⚡ Key Formulae
K-Means:Minimize: Σ ||x - μ_k||²
PCA:Maximize variance: v^T Σ v
K-Means Clustering
Hierarchical Clustering
DBSCAN
PCA
Dimensionality Reduction
Anomaly Detection
U3
Unit 3 · 6 Topics · 0% complete
Neural Networks & Deep Learning
⚡ Key Formulae
Perceptron:y = σ(Σw_i·x_i + b)
ReLU:f(x) = max(0, x)
Dropout:Randomly drop neurons with probability p
Perceptron
Activation Functions
Backpropagation
CNN Basics
RNN Basics
Overfitting & Regularization
U4
Unit 4 · 6 Topics · 0% complete
Model Evaluation
⚡ Key Formulae
Accuracy:(TP + TN) / Total
Precision:TP / (TP + FP)
Recall:TP / (TP + FN)
F1 Score:2 × (Precision × Recall) / (Precision + Recall)
Train/Test Split
Cross-Validation
Confusion Matrix
Precision, Recall, F1
ROC Curve
Bias-Variance Tradeoff
Previous Year Questions
Unit 12023 · End Semester10 marks
Implement Linear Regression from scratch in Python. Given dataset with house sizes and prices, fit a model and predict price for a new house. Calculate MSE.
Unit 22023 · End Semester8 marks
Apply K-Means clustering on given 2D dataset with k=3. Show iterations, centroids update, and final clusters. Plot the result.
Unit 42022 · End Semester6 marks
Given confusion matrix: TP=50, TN=40, FP=10, FN=5. Calculate Accuracy, Precision, Recall, and F1 Score. Which metric is best for imbalanced data?
Exam Strategy
🐍
Code in Python, not pseudocode
Exams ask for actual Python code using sklearn. Practice: model.fit(), model.predict(), train_test_split(). Import statements matter.
📐
Understand math, don't just memorize
Gradient descent, cost functions, backpropagation — understand WHY they work. Questions ask 'Derive the update rule' not just 'What is the formula'.
📊
Always plot results
Decision boundaries, loss curves, confusion matrices — visual answers earn extra marks. Use matplotlib even in exams if allowed.
⚖️
Bias-Variance is always asked
Understand overfitting (high variance) vs underfitting (high bias). Know solutions: regularization, more data, cross-validation.
Related Subjects
Semester 6
Artificial Intelligence
CS 601
Semester 2
Data Structures
CS 102
Semester 6
Big Data Analytics
CS 604