Fig 1: A CNN sequence to classify handwritten digits (src: medium) In this article, we assume that you already understand the basic concepts of a convolutional neural network (CNN), e.g. one-hot coding, convolution, pooling, fully-connected layer, activation functions. If you are totally new to these terms, please find and read our other articles. The problem We will use Tensorflow to build a...
I decided to share this topic while doing research on Deep Learning on Graph, the latest trend in Deep learning. One of the challenges that I had was to the processing power of my laptop while processing hundreds of thousands of nodes. While buying a new laptop with a good GPU is not cheap, around $2k+ US, I decided to dive into the free platform provided by Google (GG). URL: What is great about...
Most new Python programmers have a hard time figuring out the *args and **kwargs magic variables. So what are they? *args and **kwargs Firstly, it is not necessary to write *args or **kwargs. Only the * (asterisk) is necessary. You can use *var and **vars instead. Writing *args and **kwargs is just a convention. So now let’s take a look at *args first. Usage of *args *args and...
You could have been playing with this concept so many times without knowing the name of ETL. Let have a quick concept review using MovieLens automation as examples. Concept According to Wikipedia: Extract, Transform and Load (ETL) refers to a process in database usage and especially in data warehousing that: Extracts data from homogeneous or heterogeneous data sources Transforms the data for...
Quickly grasp the concept of one-hot encoding by simple data and coding. Categorical VS Numerical data Categorical data are variables that contain label values. For example, A “colour” variable can have values “red“, “green” and “blue“. Here, “red”, “green”, “blue” are labels represented by strings. Numerical data are...