Depthwise separable convolution

Depthwise Separable Convolution - How does it works?

I notice that both EfficientPS and Panoptic-DeepLab architectures uses depthwise separable convolution to reduce the total number of parameters, as a result, speed up convolution. This is a form of factorized convolutions which factorize a standard convolution into a depthwise convolution and a 1 x 1 convolution called a pointwise convolution. Depthwise separable convolution first use the depthwise convolution to applies a single filter to each input channel. Then the pointwise convolution is used to applies a 1 x 1 convolution to combine the outputs of the depthwise convolution....

August 22, 2021 · 7 min · Nguyen Tri Tai
Linear Regression

Linear Regression and a deep dive into the mathematics behind it.

Linear Regression is the most basic, well known and well understood supervised learning algorithm. It’s probably the first thing that every Machine Learning Engineer and Data Scientist come across as it lays the foundation for other sophisticated learning algorithm. But what is it? What is Linear Regression? Before knowing what is linear regression, let us get ourselves accustomed to regression. Regression is a method of modeling the relationships between a dependent variable and one or more independent variables....

May 3, 2021 · 15 min · Nguyen Tri Tai