Все публикации

0:00:57

Fully Nonlinear Neuromorphic Computing using Linear Optics

1:36:37

Lecture 29: Solomonoff's Algorithmic Probability and Theory of Induction. Conclusions/Outlook.

1:35:37

Lecture 28: Turing Machines. Algorithmic (Kolomogoroff) Complexity. Universal (Levin) Search.

1:32:38

Lecture 27: Bayesian Optimal Experimental Design. Active Learning: Gaussian Processes and Networks.

1:34:57

Lecture 26: Active Learning for Network Training: Uncertainty Sampling and other approaches.

1:33:01

Lecture 25: Reinforcement Learning: Continuous actions. Model-based. Monte Carlo Tree Search.

1:31:36

Lecture 24: Advantage Actor-Critic. Trust Regions. Proximal Policy Optimization.

1:37:06

Lecture 23: Reinforcement Learning - Policy Gradient and Q-Learning.

1:38:02

Lecture 22: Implicit Layers. Hamiltonian and Lagrangian Networks. Reinforcement Learning Overview.

1:39:51

Lecture 21: Transformers (and examples). Implicit Layers.

1:38:54

Lecture 20: Attention. Differentiable Neural Computer. Transformers.

1:30:25

Lecture 19: Graph Neural Networks. Attention Mechanisms (Basics).

0:00:40

Animation: Graph Neural Network predicting Quantum Ground States

1:28:57

Lecture 18: Recurrent Neural Networks. Graph Neural Networks.

0:00:50

Animation: Variational Autoencoder

0:02:31

Animation: Generative Adversarial Network

0:01:40

Animation: Normalizing Flow (Invertible Neural Network)

1:34:24

Lecture 17: Generative Adversarial Networks. Recurrent Neural Networks.

1:33:22

Lecture 16: Variational Autoencoder. Generative Adversarial Networks.

1:32:57

Lecture 15: Restricted Boltzmann Machines. Conditional Sampling. Variational Autoencoder.

1:33:26

Lecture 14: Boltzmann Machines (General Theory).

1:31:55

Lecture 13: Invertible Neural Networks. Convolutional and Conditional Invertible Networks.

0:45:12

Moderne Physik: 'Auf der Jagd nach kosmischen Teilchen.' (Prof. Anna Nelles)

1:32:29

Lecture 12: Mutual Information. Learning Probability Distributions. Normalizing Flows.