Neural Network Data: Patterns in Machine Learning

Visualize numeric pixel data as an image to recognize digit patterns.

Understand how neural networks interpret numerical arrays to recognize visual patterns, similar to the human brain's perception. Learn how data visualization aids in comprehending machine learning processes.

Key Insights

  • The article illustrates how numerical arrays representing images, like a handwritten number 5, are interpreted by neural networks based on the relative position and values of numbers.
  • Visualization techniques, such as displaying arrays as images without line wrapping, clarify how numerical data corresponds to visual shapes, aiding understanding of machine learning concepts.
  • The neural network identifies patterns in data similarly to how the human brain perceives visual patterns, allowing it to recognize numbers based solely on numerical relationships.

Note: These materials offer prospective students a preview of how our classes are structured. Students enrolled in this course will receive access to the full set of materials, including video lectures, project-based assignments, and instructor feedback.

Let's take one more look at this data—this array—as something that might visibly resemble a 5. We saved an image of the 5 array so that you could see how this works. The 28-item rows in the version above aren’t clearly visible as a 0 or a 5. Let me revert that to the version displaying the 5. It's kind of visible, but Jupyter Notebook is wrapping each of these lists—each of these rows—onto two lines, which makes it tough to visualize.

But we made an image to help you visualize this, where it’s not wrapped. Let’s take a look at it. Here’s the same list that we saw before, but we’ve stretched it out so that each list appears as a full row.

And now you can see—this looks like a 5. However, of course, the computer isn't going to look at this and say, "That's a 5, I see it." It’s going to have to learn based solely on the numbers, their positions relative to one another, and the intensity of each number. But this is a good visualization showing that—even just looking at the numbers—we can recognize it as a 5, even though we aren’t machine learning models ourselves.

But this is what your brain is doing. It’s similar to what the neural network is doing. It’s looking for patterns, and it’s detecting a pattern in the non-zero values here.

Data Analytics Certificate: Live & Hands-on, In NYC or Online, 0% Financing, 1-on-1 Mentoring, Free Retake, Job Prep. Named a Top Bootcamp by Forbes, Fortune, & Time Out. Noble Desktop. Learn More.

That looks kind of like a 5. And our hope is that our neural network can follow a similar process.

Colin Jaffe

Colin Jaffe is a programmer, writer, and teacher with a passion for creative code, customizable computing environments, and simple puns. He loves teaching code, from the fundamentals of algorithmic thinking to the business logic and user flow of application building—he particularly enjoys teaching JavaScript, Python, API design, and front-end frameworks.

Colin has taught code to a diverse group of students since learning to code himself, including young men of color at All-Star Code, elementary school kids at The Coding Space, and marginalized groups at Pursuit. He also works as an instructor for Noble Desktop, where he teaches classes in the Full-Stack Web Development Certificate and the Data Science & AI Certificate.

Colin lives in Brooklyn with his wife, two kids, and many intricate board games.

More articles by Colin Jaffe

How to Learn Machine Learning

Master Machine Learning with Hands-on Training. Use Python to Make, Modify, and Test Your Own Machine Learning Models.

Yelp Facebook LinkedIn YouTube Twitter Instagram