How can convolutional filters, which are designed to find spatial patterns, work for pattern-finding in sequences of words? This post will discuss how convolutional neural networks can be used to find general patterns in text and perform text classification. The end of this post specifically addresses training a CNN to classify the sentiment (positive or negative) of movie reviews.

Capsule Networks provide a way to detect parts of objects in an image and represent spatial relationships between those parts. This means that capsule networks are able to recognize the same object in a variety of different poses even if they have not seen that pose in training data. So, what is a capsule and how do they work?

Image classification is a challenging task for computers. Convolutional neural networks represent one data-driven approach to this challenge. This post will be about image representation and the layers that make up a convolutional neural network.

How and why do neural networks work? The first in a series about understanding how neural networks learn to separate and classify visual data.

I spend a lot of my time learning and creating, and I’m trying to be better about documenting the process. To that end, this post will be a summary of some projects I worked on with colleagues while I was in school and when I first began to teach.