Machine Learning — 2025 Materials

Machine Learning

Lecture Slides

FileSlidesAdditional version
01 Machine Learning and Statistical Learning.pdfSlidesAdditional version
02 Perceptron.pdfSlidesAdditional version
03 k-Nearest Neighbors.pdfSlidesAdditional version
04 Bayesian Classifiers.pdfSlidesAdditional version
06 Logistic Regression and Maximum Entropy.pdfSlidesAdditional version
07 Support Vector Machines.pdfSlidesAdditional version
09 Expectation-Maximization and Extensions.pdfSlidesAdditional version
14 Clustering Methods.pdfSlidesAdditional version
15 Singular Value Decomposition.pdfSlidesAdditional version
16 Principal Component Analysis.pdfSlidesAdditional version

Deep Learning

UnitTopicMaterials
01Overview, Linear Algebra, and NDArraySlides
03Derivatives, Backpropagation, and ComplexitySlides
04Linear Methods and OptimizationSlides
05Maximum Likelihood and Logistic RegressionSlides
06Multilayer PerceptronsSlides
08Numerical Stability, Activations, and HardwareSlides
11Convolution and PoolingSlides
12LeNet, AlexNet, VGG, and NiNSlides
13Inception, Batch Normalization, and Residual NetworksSlides
15Image Augmentation, Fine-Tuning, and Style TransferSlides
16Object Detection and Training TechniquesSlides
18Sequence ModelsSlides
19Recurrent Neural NetworksSlides
20Advanced Recurrent Neural NetworksSlides
24Attention and Vision TransformersSlides · ViT
25OptimizationSlides

Language Models

UnitTopicMaterials
00Language Model OverviewSlides
01Text PreprocessingSlides
02Statistical Language ModelsSlides
03Word EmbeddingsSlides
04Sequence-to-Sequence ModelsSlides
05Pretrained ModelsSlides

Generative Models

UnitTopicMaterials
00PrerequisitesSlides
01AutoencoderAutoencoder
02Expectation-MaximizationExpectation-Maximization
03Variational AutoencoderVariational Autoencoder
04Generative Adversarial NetworkGenerative Adversarial Network
05Diffusion ModelDiffusion Model

Other Archived Materials