# How a Neural Network Learns to Classify Images of 3s and 7s

DevFeed: [How a Neural Network Learns to Classify Images of 3s and 7s](<https://devfeed.tech/articles/hello-deep-learning-actually-learning-something-36398.md>)

Original publisher: [Read original article](<https://berthub.eu/articles/posts/first-learning/>)

Published: 2023-03-30T10:00:02Z

Content type: tutorial

Language: en

Sources: [Bert Hubert's writings](<https://devfeed.tech/sources/bert-hubert-s-writings.md>)

Topics: [Learning](<https://devfeed.tech/topics/learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [data](<https://devfeed.tech/tags/data.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [layer](<https://devfeed.tech/tags/layer.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [pixels](<https://devfeed.tech/tags/pixels.md>)

## AI overview

This tutorial explains how a simple neural network can learn to classify images of 3s and 7s. It introduces random parameter initialization, the role of the weights matrix, and adjusting weights based on image pixels to improve the classification score.

## Source excerpt

This page is part of the Hello Deep Learning series of blog posts. You are very welcome to improve this page via GitHub! In this chapter we're going to take the neural network we made earlier, but actually make it do some learning itself. And, oddly enough, this demonstration will again likely simultaneously make you wonder "is this all??" and also impress you by what even this trivial stuff can do.