Lectures related to Data Augmentation: Deep Learning

Explores Galilean transformations in spacetime, focusing on measurements and coordinate transformations.

Covers Gaussian random variables, affine transformations, and linear systems driven by Gaussian noise in multivariable control.

Explores neural networks, activation functions, backpropagation, and PyTorch implementation.

Explores isometries in Euclidean spaces, including translations, rotations, and linear symmetries, with a focus on matrices.

Covers the concept of affine transformations in functions, including shifting and compressing functions.

Explores noise sources, Fluctuation-Dissipation Theorem, amplifier noise, interference effects, and quantization error in electrical systems.

Explores Gaussian vectors, moment generating functions, independence, density functions, affine transformations, and quadratic forms.

Covers the Spike Response Model (SRM) in computational neuroscience and its relation to the adaptive leaky integrate-and-fire model.

Explores Gaussian processes, linear systems, transformations, and noise properties in multivariable control applications.

Explores the georeferencing of images, covering methodology steps, transformations, resampling, and practical application using QGIS software.

Explores noise sources in data acquisition, including thermal, shot, and amplifier noise, as well as the effects of ADC noise.

Explores noise reduction techniques in electrical systems, covering concepts like Fourier transform, impedance matching, and dithering.

Explores noise in electronics, covering average power, signal-to-noise ratio, deterministic and random signals, and noise amplification.

Explores the impact of noise in microelectronics on various circuit stages and devices.

Explores different types of noise in devices and circuits, including interference noise, inherent noise, and random signals.

Covers image processing techniques including noise addition, filtering, and image enhancement using various filters and tools.

Explores electrical metrology, covering random variables, noise sources, and their impact on electronic devices.

Covers the concept of sparse regression and the use of Gaussian additive noise in the context of MAP estimator and regularization.

Covers the Galerkin method in the Finite Element Method for solving non-homogeneous Dirichlet problems.

Provides an overview of image formation and transformation principles in computer vision.