Chapter 4 Real-world data representation using tensors

Flow-based model

Unsupervised Learning - Deep Generative Model

this post will tell you a bit more about generative models: what they are, why they are important, and where they might be going.

Learning summary 4

公开课

当我们不使用 Mac 时，一段时候后，系统先进入 sleep 状态，然后根据 hibernatemode 的模式，决定将镜像数据写入内存还是硬盘。

Chaper 1 Introducing deep learning and the PyTorch Library

That general class of algorithms we’re talking about falls under the AI subcategory of deep learning, which deals with training mathematical entities named deep neural net- works by presenting instructive examples.

Conditional Generation

控制 Generator 的输出，加入 Condition x，似的Generator 根据 x 和 z 产生 y

生成模型--Generative Model

NetWork as Generater

把 network 当作generator 使用, 特别的地方是现在 network 的输入加上一个random 的 variable Z ，Z是从某一个distribution sample 出来的。

Learning summary 3

公开课

Machine Learning 2021 Spring：

• Spatial Transformer Layer （使CNN 具有旋转平移不变性）
• RNN and LSTM

Tranformer

本质上是 sequence-to-sequence 的 model

sequence2sequence：Input a sequence, output a sequence (The output length is determined by model)