Digit Recognition
Felix Bogdanski, 13.01.2016

In the previous article we saw how a neural net can be trained to detect trends in two-dimensional charts. Since neural nets are good at learning graphical shapes, this time I want to teach a net to recognize digits from computer typesets, and to generalize to an unknown typeset. You can check the...

Natural Trend Detection
Felix Bogdanski, 12.01.2016

In the last article we compared the gaussian with a neural net. Now we research how a neural net can be applied for the detection of trends in 2d spaces. You can check the code and data on GitHub.

A trend indicates a lot of people like a certain thing. Possible use cases for detecting trends ar...

Gaussian vs. Neural Net
Felix Bogdanski, 11.01.2016

In the article Artificial Neural Networks we studied the core concepts of these powerful, universal approximators. In this article, we research how a neural net can be used instead of a gaussian for basic predictive analysis. You can check the code and data on GitHub.

This data set from the Un...

Artificial Neural Networks
Felix Bogdanski, 07.01.2016

Wolves have paws and jaws, birds feathers, the universe toroids, and we humans, well, we have our brain to build machines. Machines, capable of doing tedious tasks we no longer want to do, or to increase productivity, et cetera. We have been there before, back in industrialization times, and face a...

  • 1
  • 2