Assignments for SHALA 2020(Stay Home and Learn AI), a volunteer effort by IITB faculty.
| SNO | Assignment | Content |
|---|---|---|
| 1 | Getting started | Python data structure, Loops, Classes, Linear Algebra |
| 2 | Basic data understanding: | Data science, Central tendency, Plots, Cumulative distribution |
| 3 | Improving plots | Different types of plots, How to customize plots |
| 4 | Basic statistics | Maximum likelihood estimation, sufficient statistics, null hypothesis testing, t-test, Wilcoxon rank test |
| 5 | Introduction to ML | Machine learning problems, parameter vs. hyperparameter, overfitting, training, validation, testing, cross-validation, regularization |
| 6 | Decision Trees | Definition of a decision tree, metrics of impurity, greedy algorithm to split a node, tree depth and pruning, ensemble of trees (random forest) |
| 7 | Bayesian decision theory | Bayes rule: Prior, likelihood, posterior, evidence, Gaussian density, sufficient statistics, maximum likelihood derivation for mean and covariance |
| 8 | Linear models | linear regression and its analytical solution, loss function, gradient descent and learning rate, logistic regression and its cost, SVM hinge loss with L2 penalty |
| 9 | Kernelization | Dual form of an SVM, kernels for a dual form, examples of kernels and their typical uses, SVR in primal form, SVR in dual form |
| 10 | Feature selection and engineering | Normalization, text analysis, T-test, forward selection, features for images, features for audio, features for images, features for NLP, PCA, ZCA, K-PCA |
| 11 | Dense and shallow neural networks | Logistic regression as a sigmoid, single hidden layer using sigmoid and ReLU, approximation of any function using a single hidden layer, overfitting, advantage of multiple hidden layers, neural networks for regression, multi-regression, multi-classification using softmax, back propagation. |
| 12 | Advanced topics in neural networks | Weight initialization, momentum, weight decay, early stopping, batch SGD, advanced optimizers such as RMSprop and ADAM |
| 13 | Clustering | K-means, DB-SCAN, agglomerative clustering, scaling of dimensions, goodness of clustering |
| 14 | CNNs for Image classification | Applications of computer vision, implementation of convolution, building a convolutional neural network, image Classification using CNNs. |