Lectures related to Scale space implementation

Provable and Generalizable Robustness in Deep Learning

Explores adversarial examples, defenses, and certifiable robustness in deep learning, including Gaussian smoothing and perceptual attacks.

Image Processing I: Filters and Transformations

Explores moving average and exponential filters, Gaussian filtering, and linear scale-space concepts in image processing.

Statistical Inference and Machine Learning

Covers statistical inference, machine learning, SVMs for spam classification, email preprocessing, and feature extraction.

Digital Sustainability: Challenges and Solutions

Explores digital sustainability, multi-scale computing, and energy-efficient cloud systems.

Gaussian and Polar Representations

Covers the concepts of complex numbers, orientation, and transformations.

Signals & Systems I: Uncertainty Relations and Gaussian Impulse

Explores uncertainty relations, Gaussian impulse, pseudo-probability density, and Gabor functions in signals and systems.

Edge Detection: Basics and Techniques

Introduces the basics of edge detection, including measuring contrast, gradient images, Fourier interpretation, Gaussian functions, Canny edge detector, and industrial applications.

Learning the Kernel: Convex Optimization

Explores learning the kernel function in convex optimization, focusing on predicting outputs using a linear classifier and selecting optimal kernel functions through cross-validation.

Shape From Stereo-2

Explores stereo vision concepts such as occlusions, window size impact, multi-view stereo, dynamic shape reconstruction, and graph-based segmentation.

Spectral Estimation: Gaussian vs Binary Signals

Explores spectral estimation for Gaussian and binary signals in the spiked matrix estimation problem, analyzing the impact of signal-to-noise ratio.

Kernel Methods: Nonlinear Separation Surfaces

Explores kernel methods for nonlinear separation surfaces using polynomial and Gaussian kernels in Perceptron and SVM algorithms.

Image Processing: Neighborhood Averaging & Gaussian Smoothing

Explores neighborhood averaging, Gaussian smoothing, median filtering, contrast enhancement, and edge detection in image processing.

Image Processing: Smoothing and Filtering

Covers image smoothing, noise reduction, and segmentation techniques using filters and transforms.

Modularity and Abstraction

Explores the principles of modularity and abstraction in computer systems design, emphasizing their role in simplifying complex systems and improving scalability.

Wave Packets and Dispersion

Explores wave packets, dispersion, fast light, and superluminal group speed in optics.

MLE for Gaussian: EMV in Gaussian Model

Discusses Maximum Likelihood Estimation for Gaussian mean and variance, exploring parameter estimation in a Gaussian distribution.

Linear Phase Filters: Step Response and Characteristics

Explores linear phase filters, rise time, Gaussian filters, and rational transfer functions.

Image Filtering: Basics and Techniques

Explores image filtering techniques, including linear and nonlinear filters, for artifact removal and feature enhancement.

Kernels: Nonlinear Transformations

Explores kernels for simplifying data representation and making it linearly separable in feature spaces, including popular functions and practical exercises.

Advanced Structure Discovery: Distance Metrics and Time Series Data

Explores clustering algorithms, distance metrics, and time series data analysis techniques.