You've come to the right place! At least if blogs, articles and papers that I wrote are things that spark your particular interest.
Most of the stuff you'll find here will be implementations of deep neural nets, convolutional and recurrent neural nets,
fun little quirky projects, algorithm and datastructure implementations, and much more!
These will mainly be in C# and Python, but you could also encounter some C++, depending on what suits me at that time. Expect
a Sudoku solver (in fact, you can check that out
here, game AI agents, fun projects with Computer Vision and NLP, and whatever else that I think is worth sharing!
Sometimes I'll go deep into implementation details, other times it'll be more high level. In any case: it'll be fun to explore,
and hopefully it'll set off a spark in you! I will explain my reasoning behind what I do, and also share code, either
using code snippets, links to my GitHub repos or Jupyter notebooks you can just download.
In this article, I will make a short comparison between the use of a standard MLP (multi-layer perceptron, or feed forward network, or vanilla neural network, whatever term or nickname suits your fancy) and a CNN (convolutional neural network) for image recognition using supervised learning.
Some wise man - Jim Rohn, for the record - once said:
“Celebrate your achievements”
Automation of the automation process
I was always charmed by the idea and the practice of algorithm-heavy programming. The heavy lifting, making seemingly complex and daunting tasks run like **** of a shovel.