对于波形 \(\mathbf{x}=\{x_1,\dots,x_T\}\) 的 joint probability (联合概率)可分解为 product of conditional probabilities (条件概率乘积)，如下:
\[\displaystyle p(\mathbf{x})=\prod_{t=1}^Tp(x_t|x_1,\dots,x_{t-1})\]causal convolution / masked convolution
https://jeddy92.github.io/JEddy92.github.io/ts_seq2seq_conv/
https://github.com/JEddy92/TimeSeries_Seq2Seq/blob/master/notebooks/TS_Seq2Seq_Conv_Intro.ipynb
Conditional probability distribution
https://deepmind.com/blog/wavenet-generative-model-raw-audio/
https://arxiv.org/pdf/1806.02199.pdf
Deep Self-Organization: Interpretable Discrete Representation Learning on Time Series
PixelCNN http://sergeiturukin.com/2017/02/22/pixelcnn.html
Auto-Regressive Generative Models (PixelRNN, PixelCNN++) https://towardsdatascience.com/auto-regressive-generative-models-pixelrnn-pixelcnn-32d192911173
https://towardsdatascience.com/3-facts-about-time-series-forecasting-that-surprise-experienced-machine-learning-practitioners-69c18ee89387
Comments