Skip to main content
HOME
www.lmu.de
Fakultät 11
Unterrichtsmitschau
Shop
Aktuelle Vorlesungen
Alle Vorlesungen
FAQs
Tutorials
Machine Learning
Model Selection and Estimation of the Generalization Cost (cont.) // Bayesian Networks: Construction, Inference, Learning and Causal Interpretation // Deep X: Deep Learning with Deep Knowledge
(00:00:00)
>
Introduction and recapitulation
(00:36:55)
>
A: Classical Frequentist Approaches: Akaikes Information Criterion (AIC)
(00:42:17)
>
B: Bayesian Approaches
(00:56:43)
>
C: Modern Frequentist Approaches
(01:10:39)
>
Bayesian Networks: Construction, Inference, LEarning and Causal Interpretation
(01:25:21)
>
Deep X: Deep Learning with Deep Knowledge
Recording from:
05.07.2018
Lecturer:
Volker, Tresp
Model Selection and Estimation of the Generalization Cost
(00:00:00)
>
Introduction and recapitulation
(01:02:00)
>
Model Selection and Estimation of the Generalization Cost
(01:23:07)
>
Learning Theories
(01:36:02)
>
A: Classical Frequentist Approach
Recording from:
28.06.2018
Lecturer:
Volker, Tresp
Frequentist Statistics and Bayesian Statistics (cont.) // Linear Classification // Optimal Separating Hyperplane and the Support Vector Machine
(00:00:00)
>
Introduction and recapitulation
(00:34:54)
>
Bayesian Statistics
(00:47:19)
>
Linear Classification
(01:29:53)
>
Logistic Regression in Medical Statistics
(01:42:38)
>
Optimal Separating Hyperplane and the Support Vector Machine
Recording from:
21.06.2018
Lecturer:
Volker, Tresp
Factorization, Principal Component Analysis and Singular Value Decomposition
(00:00:00)
>
Introduction and recapitulation: Linear Regression and Unknown Inputs
(00:07:43)
>
Factorization
(00:18:20)
>
PCA
(00:38:42)
>
PCA Applications
(00:42:52)
>
PCA Example: Handwritten Digits
(00:49:32)
>
Eigenfaces: similarity search of images
(00:57:50)
>
PCA and Singular Value Decomposition
(01:09:43)
>
Application: Similarities Between Documents
Recording from:
14.06.2018
Lecturer:
Florian Buettner
Some Concepts of Probability (Review) // Frequentist Statistics and Bayesian Statistics
(00:00:00)
>
Introduction and recapitulation
(00:33:55)
>
Some Concepts of Probability (Review)
(01:31:31)
>
Frequentist Statistics
(02:06:55)
>
Bayesian Statistics
Recording from:
07.06.2018
Lecturer:
Volker, Tresp
Deep Learning
(00:00:00)
>
Introduction and Overview
(00:04:36)
>
Introduction to Deep Learning
(00:30:27)
>
Implementation of a Deep Learning Model
(00:38:41)
>
Basic Building Blocks
(01:06:04)
>
Thinking in Macro Structures
(01:15:28)
>
End-to-End Model Design
(01:19:27)
>
Deep Learning Model Training
(01:25:32)
>
Loss Function Design
(01:33:37)
>
Optimization
(01:51:28)
>
Regularization
(01:53:12)
>
Additional Notes
Recording from:
24.05.2018
Lecturer:
Dr. Denis Krompaß
Feature Spaces, Manifolds, and Deep Generative Models (cont.) // Kernels
(00:00:00)
>
Introduction and recapitulation
(00:14:29)
>
Feature Spaces, Manifolds, and Deep Generative Models (cont.)
(00:58:41)
>
Kernels
Recording from:
17.05.2018
Lecturer:
Volker, Tresp
Deep Learning // Feature Spaces, Manifolds, and Deep Generative Models
(00:00:00)
>
Introduction and recapitulation
(00:37:10)
>
Deep Learning
(01:14:03)
>
Convolutional Neural Networks (CNNs)
(01:40:08)
>
Feature Spaces, Manifolds, and Deep Generative Models
Recording from:
03.05.2018
Lecturer:
Volker, Tresp
Basis Functions // Neural Networks
(00:00:00)
>
Introduction and recapitulation
(00:27:54)
>
Basis Functions
(01:17:43)
>
Neural Networks
Recording from:
26.04.2018
Lecturer:
Volker, Tresp
The Perceptron // Linear Algebra (Review) // Linear Regression
(00:00:00)
>
Introduction and recapitulation
(00:31:09)
>
The Perceptron
(01:23:16)
>
Linear Algebra (Review)
(01:34:41)
>
Linear Regression
Recording from:
19.04.2018
Lecturer:
Volker, Tresp
Introduction
(00:00:00)
>
Introduction
(00:21:06)
>
Non-Technical Perspectives on Learning: Philosophy
(00:50:56)
>
Non-Technical Perspectives on Learning: Psychology, Cognition and Cognitive Neuroscience
(01:17:14)
>
Non-Technical Perspectives on Learning: Cellular Neuroscience
(01:26:18)
>
Machine Learning: Before the Computer Age to Today: Statistics
(01:35:56)
>
Machine Learning: Neural Computation I (Perceptron)
(01:41:10)
>
Machine Learning: Classical Artificial Intelligence
(01:50:34)
>
Machine Learning: Neural Computation II (Multilayer Perception)
(01:56:20)
>
Machine Learning: Mathematically Wee-Founded Models
(01:57:34)
>
Machine Learning: Neural Computation III (Deep Learning
(02:04:31)
>
Details on the Lecture
Recording from:
12.04.2018
Lecturer:
Volker, Tresp
RSS-Feed abonnieren:
