วีดีโอ

Principal Component Analysis: - Linear Projection - Maximal Projection Variance - Minimal Reconstruction Error - Rayleight Quotient of Covariance Matrix - Eigenvalue Decomposition.

Deep Learning Lecture 1.2 - Intro Shallow ML

Deep Learning Lecture - Intro Conclusion

Deep Learning Lecture Introduction: - Artifical neurons as feature detectors - Deep Learning - Convolutional Neural Networks

Deep Learning Lecture Intro: - Unsupervised Learning - Autoencoders - Generative Learning - Variational Autoencoders - Generative Adversarial Networks

Deep Learning Lecture - Practicalities - Data preparation - A typical ML pipeline - Key ML advances to facilitate deep learning - Deep vs shallow learning

Deep Learning Lecture: Optimization Methods - Stochastic Gradient Descent (SGD) - SGD with Momentum

Deep Learning Lecture - Estimator Theory - Linear least squares (LLS) as an example - Learning problem and loss function - Parameter estimation - Closed-form solution for LLS

Deep Learning Lecture - Estimator Theory 3: - Statistical Estimator Theory - Bias, Variance and Noise - Results for Linear Least Square Regression

Deep Learning Lecture: Optimization Methods - Gradient Descent (GD) - Newton's Method - Choosing the GD step size

Unsupervised Learning 1: PCA and Autoencoders

Deep Learning Lecture Introduction: - Neural Networks - Backpropagation

Deep Learning Lecture - Estimator Theory 2 - Prediction / Validation / Testing - Hyperparameter Selection

Deep Learning Lecture Intro: Greetings

Convolutional Neural Networks - Motivation by classical Neuroscience - Simple and Complex V1 cells - Gabor Functions - Grandmother and Halle Berry Cells

Deep Learning Lecture 3.2 - Neural Network Basics

Deep Learning Lecture 5.1 - Greetings

Deep Learning Lecture 2.5 - Regularization

Deep Learning Lecture 6.3 - PCA part 2

Deep Learning Lecture 4.4 - RMSprop & Adam

Deep Learning Lecture 3.3 - Universal Representation Theorem

Deep Learning Lecture 5.3 - ConvNets

Deep Learning Lecture 3.1 - Greetings

Deep Learning Lecture 4.1 - Greetings

Deep Learning Lecture 5.2 - Convolutions

Deep Learning Lecture 3.4 - Backpropagation

Deep Learning Lecture 2.1 - Greetings

Deep Learning Lecture 6.4 - Autoencoders

Deep Learning Lecture 7.1 - Greetings