Building a Brain: A How-to Guide on Capsule Neural Networks

Capsule Neural Networks

By Morven Watt

 

Imagine a tree. Now name the parts.

You probably listed things like roots, trunk, branches, leaves, twigs. Ask a hundred people, and you’ll mostly get the same answers. Ask people around the world and they’ll likely name the exact same universal parts.

When asked to think about a tree, a picture of a tree with all its composite parts popped into your head without much effort. But there’s a lot more going on in your brain than populating a simple image.

 

If you look at the human brain, specifically the higher order functions of the frontal cortex, you see that it includes things like planning, language, and problem-solving. It’s also where we learn to decode the complexities of the world around us. We start problem-solving early in life and build on that existing framework as our brains grow. One of the key ways we do this is by organizing and categorizing the things in our world.

 

When we learn about the leaves on the trees, we learn them in the context of the twigs and branches they grow from. When we learn about trees, we refer back to learning about leaves and the other smaller elements, creating our own categories and distinctions. “This is a tree and I know this is a tree, even if I don’t explicitly see all of it.” We can still identify trees from a distance, or if we only see a canopy, fallen branch, or trunk.

 

To put this another way, any complex object is a hierarchy of simpler objects.

 

This is essentially what Capsule Neural Networks (CNN) aim to do. CNNs are a type of Artificial Neural Network (ANN) that mimic the human brain and the way we categorize and process information in order to better process this hierarchical model of relationships.

 

But how does this actually work?

 

Let’s break down the steps using our tree example.

 

Step 1. We add structures known as “capsules” to a Convolutional Neural Network (ConvNet). So “leaf” would be a capsule, as would “twig,” “branch,” “truck,” “roots,” etc. These would be considered “lower order capsules.”

 

Step 2.We show our ConvNet an image of a tree.

 

Step 3. We use the output from the lower order capsules to form a more stable representation for higher order capsules. Our lower order capsules would identify leaves, twigs, branches, and so on, and pass them to the higher order capsule.

 

Step 4. This then allows the higher order capsule to produce an output, which is a vector of probability of an observation and a pose for that observation. In a nutshell, it allows the machine to say “Hey, this image has leaves, twigs, and branches. It’s probably a tree.”

 

What’s great about this type of technology is how it can be used to solve problems, like the Picasso Problem. This refers to the fact that an image can have all the right parts, but not in the correct spatial relationship, like most Picasso paintings. Or, in the context of our tree, if an image were to have unusual looking trees, or spatial inconsistencies, image recognition becomes compromised.

 

This is because max-pooling is used in traditional ConvNets. Max-pooling refers to what happens between convolutional layers. Max-pooling layers take the most active neurons from each convolutional layer and pass them on to the next convolutional layer.

 

1A Convolutional Neural Network (ConvNet) is a class of deep neural network most commonly applied to analyzing visual imagery.

 

The problem? The neurons that are less active are dropped. This means spatial information gets lots as data progresses through the network. CNNs help solve this problem because they encapsulate all the important information of an image. Because capsules are independent, when multiple capsules agree, the probability of correct detection is much higher.

 

This is the (basic) principle of CNN technology and how it can propel future learning is fascinating. Image identification can help us understand and analyze the vast amounts of data that already exist, and the new data that is constantly being created. While it may seem that CNNs are simply identifying images, the fact is, we’re creating technologies that can operate more and more like a human brain.

 

As Pliny the Elder wrote, “The brain is the citadel of the senses; this guides the principle of thought.” When it comes to machine learning, we’re building citadels, and every data scientist has the chance to be an architect for the future of machine learning and AI.

 

Share on twitter
Share on facebook
Share on linkedin
Vithya Venkatasubbu

Vithya Venkatasubbu

More from Pragmatic

Related Content

Recommended Content

Trending Content

Virtual conference, morning meeting online. A young woman is using app on pc for connection with colleagues, employees, she is writing in notebook. Video call with many multiracial people togethe

How to Overcome 8 Common Market Visit Barriers

For many reasons, you might find it hard to get face-to-face with customers and prospective customers. We’re going to outline a more sustainable path that overcomes these common problems. We’ll even discuss some advantages if we think of these circumstances not as constraints but as opportunities. 

VIEW
A person scheduling market visits

A Meeting Scheduling System for Market Visits

So, why talk about the mechanics of setting up meetings? The simple answer is the act of setting up meetings with buyers and users is time-consuming and difficult. I work with clients all the time who keep reporting that the actual process of setting meetings with their buyers or their users can be an impediment to achieving a specific quantity of meetings they want to have in a given quarter.  But, if you don’t get meetings, the NIHITO principle is limited in its impact. I’m going to share strategies to identify your audience and effectively set up meetings. 

VIEW

Sign up to stay up to date on the latest industry best practices.

Training on Your Schedule

Fill out the form today and our sales team will help you schedule your private Pragmatic training today.

First Name*
Last Name*
Email Address*
Phone
Company
Job Title
Location
How can we help you?
Preferred method of contact
Privacy Policy*

Training on Your Schedule

Fill out the form today and our sales team will help you schedule your private Pragmatic training today.

First Name*
Last Name*
Email Address*
Phone
Company
Job Title
Location
How can we help you?
Preferred method of contact
Privacy Policy*

Subscribe

Subscribe

Download Now

Stay Informed

Sign up to stay up-to-date on the latest industry best practices. Get content such as:

    • The Pragmatic – Industry insider magazine
    • The ever-growing webinar series 
    • Our world-class podcast series

Subscribe