DBATU · Third Year B.Tech Information Technology · NEP 2020
Machine Learning
26AF1246PE608A · Elective III · Semester VI · 3 credits · Continuous assessment 20 + mid-semester 20 + end-semester 60
One of the Elective III options.
Unit 1: Introduction to Machine Learning
8 hoursTypes of learning and applications; AI, ML and data science; traditional programming versus ML; concept learning; evaluating hypotheses; the Find-S and candidate-elimination algorithms; probability theory.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- AI, ML, deep learning and data science
- Machine learning workflow
- Concept learning: Find-S and candidate elimination
- Evaluating hypotheses
Unit 2: Supervised and Unsupervised Learning
9 hoursBinary and multiclass classification; Bayes' theorem, decision trees, naïve Bayes, SVM and k-NN; linear and logistic regression; clustering, k-means and hierarchical clustering; reinforcement learning.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Decision trees
- K-nearest neighbours and naïve Bayes
- Support vector machines
- Linear and polynomial regression
- Logistic regression
- K-means clustering
- Hierarchical clustering and DBSCAN
- Introduction to reinforcement learning
Unit 3: Model Evaluation and Selection
9 hoursFeature engineering; PCA and LDA; bias and variance; training and testing; overfitting and Occam's razor; regularisation and model selection; autoencoders; L2 regularisation, early stopping, data augmentation and dropout.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- PCA and dimensionality reduction
- Linear discriminant analysis
- Bias–variance trade-off and responsible AI
- Cross-validation and hyperparameter tuning
- Regularisation, early stopping and dropout
Unit 4: Deep Learning
8 hoursThe McCulloch–Pitts neuron and threshold logic; perceptrons and their learning algorithm; multilayer perceptrons and sigmoid neurons; feedforward networks; backpropagation; gradient descent with momentum, Nesterov, stochastic, AdaGrad, RMSProp and Adam.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Perceptrons and multilayer perceptrons
- Backpropagation in feedforward networks
- Gradient descent optimisers: momentum to Adam
Unit 5: Deep Learning Architectures
6 hoursLeNet, AlexNet, ZF-Net, VGGNet, GoogLeNet and ResNet; visualising and fooling CNNs; recurrent networks and backpropagation through time; vanishing and exploding gradients; GRU and LSTM.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- CNN architectures: LeNet to ResNet
- Visualising convolutional networks
- Recurrent networks and backpropagation through time
- LSTM and GRU
Unit contents are summarised from the official DBATU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Technological University (DBATU).