Courses/Computer Vision

Computer Vision

CSE471

Prof. Makarand Tapaswi + Prof. Charu Sharma•Spring 2025-26•4 credits

Revision Notes/Unit 3 — Machine Learning Recap

Unit 3 — Machine Learning Recap

Setup → logistic regression → neural networks + backprop → training tricks (BN, dropout, init, LR schedule) → ensembles (bagging vs boosting) → density estimation (GMM via EM) → RNNs / LSTM / GRU → metrics (Precision, Recall, F1, AP/mAP, ROC vs PR) → kNN → linear & polynomial regression → PCA / SVD → clustering (k-means, GMM, hierarchical). The ML toolbox CV is built on top of.

ML — Logistic, NN+Backprop, Ensembles, Density, RNN, Metrics, kNN, Regression, PCA/SVD, Clustering

26 min

ML in this course is the bag of mathematical tools that turn data into a function. Three task families: **supervised** (X → Y; classification, regression), **unsupervised** (X alone; clustering, density, dimensionality reduction), **reinforcement** (X → action with reward; not the focus here). The key tools — logistic regression, the multilayer perceptron with backprop, PCA, k-means — show up inside every modern CV system as building blocks (a softmax head IS multinomial logistic regression; a CNN backbone IS hierarchical MLP with weight sharing).