What are Convolutions?

Introduction

After writing my article over how to build a CNN, I forgot that I should've explained what a convolution is, in terms of image recognition. 

What are Convolutions?

They are essentially manners of seeing the probability of a distinct set of figures. Suppose we have 2 lists, 

["parrot","dog","cat"] ; ["bagel","bread","cheese"]

What is the probability of getting a bagel? 


(3/9, or ~33%)




What is the probability of getting a cat or a bagel? 
(5/9, or ~56%)

This is what a convolution tries to do. 


In the context of image generation, we use a kernel, a matrix to look over every pixel (if you decide to keep it that way) of the image with certain values. The kernel will scan every pixel and then form a new matrice constructed with the scan of the pixels that want to be highlighted. 

 
(It's the number 2)


There is also this thing called stride when it comes to kernels. Stride is used to tell the kernel how many pixels it should move. For example, a stride of 1 will make it move 1 pixel at a time. Two pixels will make it move every two pixels. This means some pixels are skipped. The example above uses a stride of 1. You also have padding, which is to add extra pixels to an image to preserve the dimensions of the image. 

Using convolutional layers instead of, normal, linear layers are very good for image recognition. Instead of having random algorithms looking for random pixels, we have a kernel scanning for something specific. That's why Convolution Layers can be beneficial! They can also be mixed with several different other layers to help your network. 

Works Referenced/Extra Resources

These were the works I referenced while researching for this article. I also included some other resources that I thought would be beneficial for everybody. 

"Convolutional Neural Networks Explained (CNN Visualized)" by Futurology – An Optimistic Future.

"What are convolutional neural networks?" by IBM.

"All about convolutions, kernels, features in CNN" by Abhishek Jain (Medium).

"CNN | Introduction to Padding" by savyakhosla (accessed Sept 8, 2024, GeeksforGeeks)

Comments

Post a Comment

Popular posts from this blog

What is a Multimodal LLM?

Image
Introduction Multimodal is the ability for a model to process several different types of inputs. For example, ChatGPT can support text input as well as image input as one combined input. You could also have a model take in .pdf, .md, and input text as inputs (yes, these count as different modalities).  This allows for users to give represent different ideas in its rawest form possible, such as an image, instead of describing it. If you try to describe it, you could hit hurdles in trying to properly explain it and making sure it interpreted the description correctly.  How do Multimodal LLMs work?  Typically, these modalities are "fused" together. Here's an architecture diagram,  Image from NVIDIA In this case, we have an encoder for a specific modality (e.g. video encoder, image encoder, audio encoder). This encodes them into embeddings the LLM can understand and use. After encoding each specific modality, we then fuse them together. Then, the output is projected and ...
Read more

Top 3 Breakthroughs in Computer Vision in 2024

Image
Introduction Over the past few year, AI has become popular; however, no year matches the pace of the past few years. 2024 was an extremely crucial year for Computer Vision, with new models and breakthroughs occurring rapidly. Today, I'll be talking about the 3 biggest advancements in the Computer Vision field during 2024.  3. Vision Language Modeling Simply put, Vision Language Models, or VLMs for short, are Large Language Models (LLMs) that take an image and/or text as input. Think of ChatGPT, where you import an image and then type out a question that you have over the image. It will be able to understand both and output an answer. These are also what you would call a "multimodal model," which is a model that can understand multiple different types of sources/inputs.  Although Vision Language Models have existed for a while, they have recently become better and more accurate. However, this doesn't mean it's all sunshine an rainbows: there are still several barri...
Read more

A Mathematical Explanation of Gradient Descent

Image
Example of a close-to-optimal Gradient descent for a quadratic function. Credit: Dylan Introduction Although I wrote an article recently explaining Gradient Descent, I feel like a mathematical explanation of how it works would be beneficial not only to understand how it works, but also how you derive the functions.  Explanation First, we need a way to calculate how far off the model is. For our example, we will use the L2 Loss Function,  Let N represent the total amount of data points we have, i the iteration we are on, yᵢ represent the expected output, and ŷ represent the output predicted by the model.  Let's look more into ŷ. Since ŷ is the predicted value, this is the function that needs to have their parameters changed. Our goal is to change these parameters enough to minimize the loss of ŷ. For our example, let's set ŷ to be a linear line.  The values in "a" and "b" are our parameters. These will be the values we will have to change within f(x) to chang...
Read more