- The document is a summary of a meeting about deep learning using Python. It includes an agenda of topics to be covered such as basic neural network concepts, cross entropy, convolutional neural networks, and trying Keras.
- It also provides information about a Slack team created for further discussion and questions, and encourages participation. Prerequisites and explanations of key concepts like neurons and convolution are also summarized.
- The document is a summary of a meeting about deep learning using Python. It includes an agenda of topics to be covered such as basic neural network concepts, cross entropy, convolutional neural networks, and trying Keras.
- It also provides information about a Slack team created for further discussion and questions, and encourages participation. Prerequisites and explanations of key concepts like neurons and convolution are also summarized.
1. The document discusses probabilistic modeling and variational inference. It introduces concepts like Bayes' rule, marginalization, and conditioning.
2. An equation for the evidence lower bound is derived, which decomposes the log likelihood of data into the Kullback-Leibler divergence between an approximate and true posterior plus an expected log likelihood term.
3. Variational autoencoders are discussed, where the approximate posterior is parameterized by a neural network and optimized to maximize the evidence lower bound. Latent variables are modeled as Gaussian distributions.
19. 準備
前提
オペレーティングシステムは
1. Linux (Ubuntu 14.04, 16.04 推奨)
2. Mac OSX (El capitan 推奨)
3. Windows (7, 8, or 10). You might be able to do with Windows XP as well in principle, but I do
not recommend do this.
を仮定させていただきます。それ以外での 動作は考えない ことにします。加えて TensorFlow は公
式には Windows をサポートしていません。 従いまして Windows をお使いの場合には使用制限が
あるとお考えください。 Windows 環境でTensorFlow をお使いになる場合には,なんらかの仮想環
境を必要とします。
準備
以下のインストールを済ませてください。最低でもpythonがインストールされている必要がありま
す。OSによってはPythonがプレインストールされていますが,多くのチュートリアルではOSに付