Convolutional Models for Sequential Data

Easing Into Recurrent Neural Networks

Remember these two useful properties of Convolutional Models.

So if we take the translation invariance property and apply it to sequential data, such as text or time series data. We can get really nice pattern recognition program.

An image is a plane or a two dimensional object, whereas a sequential data is a line or a one dimensional object.

However, even simple objects like lines can have regularity and patterns. If instead of 2D convolutional layers, we use 1D convolutional layers, we can get a pretty neat text classifier or timeseries forecaster.

The 1D convolutional layer would be primarily finding subsections of the complete data, then analyzing it, and finding other similar subsections.

For example, in the data above, the convolution layer would find 6 different subsections all very similar.

Related posts:

Que a poesia nos salve da dor de viver cada hora Que a poesia alcance o âmago de cada ser e recupere a alegria que mora em cada íntimo, reforça a alma e revigora o viver. Escrevo para dividir a…

To be successful in business or to sell more first you need to understand who your Customer is. Without knowing your ideal customer you can sell nothing. Most of the beginner startups or marketers…

Semenjak adanya pandemi Covid-19, banyak perusahaan yang mengijinkan para karyawannya untuk bekerja dari rumah atau yang sekarang lebih populer dengan sebutan WFH alias Work From Home. Apakah kantor…