Animation: Variational Autoencoder
A variational autoencoder is a type of neural network that learns to compress (encode) data, in such a way that one can later randomly sample data.
Here we show training of a variational autoencoder on a data set of wave packets that have been placed with a random location and amplitude. Upper left: test set, with VAE decoder results shown in orange; upper right: latent space distribution, with color coding for actual location (left) or amplitude (right) of any data point; lower right: latent space distributions for the few samples from the test set (in each case, the Gaussian spread in latent space is also indicated); lower left: loss evolution.
2021 by Florian Marquardt. For the full explanation, watch https://www.youtube.com/watch?v=bSta4s439-I .
This animation is part of the online lecture series "Advanced Machine Learning for Physics, Science, and Artificial Scientific Discovery". See the website https://pad.gwdg.de/s/2021_AdvancedMachineLearningForScience# and the channel with the full lecture videos: https://www.youtube.com/playlist?list=PLemsnf33Vij4-kv-JTjDthaGUYUnQbbws.
Видео Animation: Variational Autoencoder канала Florian Marquardt
Here we show training of a variational autoencoder on a data set of wave packets that have been placed with a random location and amplitude. Upper left: test set, with VAE decoder results shown in orange; upper right: latent space distribution, with color coding for actual location (left) or amplitude (right) of any data point; lower right: latent space distributions for the few samples from the test set (in each case, the Gaussian spread in latent space is also indicated); lower left: loss evolution.
2021 by Florian Marquardt. For the full explanation, watch https://www.youtube.com/watch?v=bSta4s439-I .
This animation is part of the online lecture series "Advanced Machine Learning for Physics, Science, and Artificial Scientific Discovery". See the website https://pad.gwdg.de/s/2021_AdvancedMachineLearningForScience# and the channel with the full lecture videos: https://www.youtube.com/playlist?list=PLemsnf33Vij4-kv-JTjDthaGUYUnQbbws.
Видео Animation: Variational Autoencoder канала Florian Marquardt
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Lecture 4: Loss functions. Overfitting. Dropout. Adaptive Gradient Descent. Convolutional networks.](https://i.ytimg.com/vi/pO8U2ET_8P0/default.jpg)
![Lecture 26: Active Learning for Network Training: Uncertainty Sampling and other approaches.](https://i.ytimg.com/vi/fwHZtqr-uBY/default.jpg)
![Lecture 23: Reinforcement Learning - Policy Gradient and Q-Learning.](https://i.ytimg.com/vi/lXSu5rrBvsc/default.jpg)
![Lecture 14: Boltzmann Machines (General Theory).](https://i.ytimg.com/vi/FEF0_lqaXco/default.jpg)
![Lecture 19: Graph Neural Networks. Attention Mechanisms (Basics).](https://i.ytimg.com/vi/nyKuAm-HWn4/default.jpg)
![Lecture 10: Inductive Bias. Fisher Information. Information Geometry.](https://i.ytimg.com/vi/majazrx0LKQ/default.jpg)
![Moderne Physik: "Auf der Jagd nach kosmischen Teilchen." (Prof. Anna Nelles)](https://i.ytimg.com/vi/SUt8CTaKa0g/default.jpg)
![Lecture 21: Transformers (and examples). Implicit Layers.](https://i.ytimg.com/vi/Q4Rn3IZ6a4k/default.jpg)
![Lecture 12: Mutual Information. Learning Probability Distributions. Normalizing Flows.](https://i.ytimg.com/vi/L0vyq91cUfg/default.jpg)
![Talk: Discovering feedback strategies for open quantum systems via deep reinforcement learning](https://i.ytimg.com/vi/zmh8P9eork0/default.jpg)
![Machine Learning for Physicists (Lecture 3): Training networks, Keras, Image recognition](https://i.ytimg.com/vi/1uLzkX19zPc/default.jpg)
![Lecture 16: Variational Autoencoder. Generative Adversarial Networks.](https://i.ytimg.com/vi/bSta4s439-I/default.jpg)
![Lecture 11: Natural Gradient. Kullback-Leibler Divergence. Mutual Information.](https://i.ytimg.com/vi/iV_DDxtmwEE/default.jpg)
![Lecture 15: Restricted Boltzmann Machines. Conditional Sampling. Variational Autoencoder.](https://i.ytimg.com/vi/2bM9oZdCfk8/default.jpg)
![Machine Learning for Physicists (Lecture 5): Principal Component Analysis, t-SNE, Adam etc., ...](https://i.ytimg.com/vi/Mx0GMr_3Z4U/default.jpg)
![Lecture 25: Reinforcement Learning: Continuous actions. Model-based. Monte Carlo Tree Search.](https://i.ytimg.com/vi/RQyKOFi6_MA/default.jpg)
![Lecture 7: Contractive Autoencoder. Shannon's Information Theory: Compression and Information.](https://i.ytimg.com/vi/Ihcruy9gX70/default.jpg)
![Lecture 27: Bayesian Optimal Experimental Design. Active Learning: Gaussian Processes and Networks.](https://i.ytimg.com/vi/HJ6VbqwLh3Q/default.jpg)
![Lecture 22: Implicit Layers. Hamiltonian and Lagrangian Networks. Reinforcement Learning Overview.](https://i.ytimg.com/vi/LvskOij7YXE/default.jpg)
![Lecture 20: Attention. Differentiable Neural Computer. Transformers.](https://i.ytimg.com/vi/BvWuYqEI5p0/default.jpg)