- 動画数
- 1,111
- チャンネル登録者
- 184万
- 総再生回数
- 1.7億
- 最新のアップロード
- 2026/11/14
- 独立ページ
- Machine Learning
- コンテンツの言語: 英語
- 地域: ハンガリー
これは Youtop が運営する独立したディレクトリページです。Two Minute Papers や YouTube が運営・後援・承認しているものではありません。 修正を提案する. このクリエイター本人ですか？ページを申請する
Loading
これは Youtop が運営する独立したディレクトリページです。Two Minute Papers や YouTube が運営・後援・承認しているものではありません。 修正を提案する. このクリエイター本人ですか？ページを申請する
Two Minute Papers · 2016年8月11日 公開
Autoencoders are neural networks that are capable of creating sparse representations of the input data and can therefore be used for image compression. There are denoising autoencoders that after learning these sparse representations, can be presented with noisy images. What is even better is a variant that is called the variational autoencoder that not only learns these sparse representations, but can also draw new images as well. We can, for instance, ask it to create new handwritten digits and we can actually expect the results to make sense! _____________________________ The paper "Auto-Encoding Variational Bayes" is available here: http://arxiv.org/pdf/1312.6114.pdf Recommended for you: Recurrent Neural Network Writes Sentences About Images - https://www.youtube.com/watch?v=e-WB4lfg30M Andrej Karpathy's convolutional neural network that you can train in your browser: http://cs.stanford.edu/people/karpathy/convnetjs/demo/cifar10.html Sentdex's Youtube channel is available here: https://www.youtube.com/user/sentdex Francois Chollet's blog post on autoencoders: https://blog.keras.io/building-autoencoders-in-keras.html More reading on autoencoders: https://probablydance.com/2016/04/30/neural-networks-are-impressively-good-at-compression/ WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE: David Jaenisch, Sunil Kim, Julian Josephs, Daniel John Benton, Dave Rushton-Smith, Benjamin Kang. https://www.patreon.com/TwoMinutePapers We also thank Experiment for sponsoring our series. - https://experiment.com/ Subscribe if you would like to see more of these! - http://www.youtube.com/subscription_center?add_user=keeroyz Music: Dat Groove by Audionautix is licensed under a Creative Commons Attribution license (https://creativecommons.org/licenses/by/4.0/) Artist: http://audionautix.com/ Thumbnail background image source (we have edited the colors and edited it some more): https://pixabay.com/hu/fizet-sz%C3%A1mok-sz%C3%A1mjegyek-kit%C3%B6lt%C3%A9s-937882/ Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu Károly Zsolnai-Fehér's links: Facebook → https://www.facebook.com/TwoMinutePapers/ Twitter → https://twitter.com/karoly_zsolnai Web → https://cg.tuwien.ac.at/~zsolnai/
