This media is not supported in your browser
VIEW IN TELEGRAM
Dreamer learns to solve 20 challenging continuous control tasks with image inputs, 5 of which are displayed here. The visualizations show the same 64x64 images that the agent receives from the environment.
Более эффективная предварительная тренировка модели НЛП с помощью ELECTRA
https://github.com/google-research/electra
https://github.com/google-research/electra
Forwarded from Книги для программистов
Глубокое обучение.pdf
14.2 MB
Генеративные Модели
https://openai.com/blog/generative-models/
https://openai.com/blog/generative-models/
Openai
Generative models
This post describes four projects that share a common theme of enhancing or using generative models, a branch of unsupervised learning techniques in machine learning. In addition to describing our work, this post will tell you a bit more about generative…
Generative Adversarial Imitation Learning
https://github.com/openai/imitation
https://github.com/openai/imitation
GitHub
GitHub - openai/imitation: Code for the paper "Generative Adversarial Imitation Learning"
Code for the paper "Generative Adversarial Imitation Learning" - GitHub - openai/imitation: Code for the paper "Generative Adversarial Imitation Learning"
SimpleGAN — Train GANs with 3 lines of code - Towards Data Science
https://towardsdatascience.com/simplegan-train-gans-with-3-lines-of-code-c221bbf244
https://towardsdatascience.com/simplegan-train-gans-with-3-lines-of-code-c221bbf244
Medium
SimpleGAN — Train GANs with 3 lines of code
A framework based on TensorFlow to ease training of generative models
Творческое сотрудничество человека и машины. Playform - это новый способ для художников экспериментировать c ИИ - кодирование не требуется.
https://www.playform.io/
https://www.playform.io/