What is each individual filter doing in a Convolutional Neural Network? Which kinds of images is it learning to detect? Here’s a way to know

According to Wikipedia, apophenia is “the tendency to mistakenly perceive connections and meaning between unrelated things”. It is also used as “the human propensity to seek patterns in random information”. Whether it’s a scientist doing research in a lab, or a conspiracy theorist warning us about how “it’s all connected”, I guess people need to feel like we understand what’s going on, even in the face of clearly random information.

Deep Neural Networks are usually treated like “black boxes” due to their inscrutability compared to more transparent models, like XGboost or Explainable Boosted Machines.

However, there is a way to interpret what each individual filter is doing in a Convolutional Neural Network, and which kinds of images it is learning to detect. …


Luciano Strika

Computer Science student at Buenos Aires University, Data Scientist at MercadoLibre. I also write about Machine Learning and Data on www.datastuff.tech

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store