Author’s Note: This article does not explicitly walk through the math behind each optimizer. This article’s focus is to conceptually walk-through each optimizer and how they perform. If you don’t know what gradient descent is, check out this link before continuing with the article.

Stochastic Gradient Descent (SGD)

Visualization of Gradient Descent

SGD is the default optimizer for the python Keras library as of this writing. SGD differs from regular gradient descent in the way it calculates the gradient. Instead of using all the training data to calculate the gradient per epoch, it uses a randomly selected instance from the training data to estimate the gradient. …


In this article I will discuss an analogy that I find very helpful when trying to comprehend what PCA is doing.

BACKGROUND

PCA is a dimensionality-reduction algorithm. Reducing dimensionality matters because of the “curse of dimensionality.” Boiled down, the “curse of dimensionality” essentially means too many features is a bad thing. The two main problems that occur with large dimensionality are prolonged training times and overfitting.

It is easy to comprehend how increasing the number of features would increase training times. More things for the computer to digest = more time. On the other hand, overfitting can be less straightforward. Overfitting…


“Farming is a profession of hope.” — Brett Brian

Artificial Intelligence (AI), as you may already know, is the simulation of intelligence by machines. If this is a new topic for you, don’t worry, we will talk more about the specifics of AI in a moment. For now, know that this ‘intelligence’ is revolutionizing farming.

It is not an overstatement that farming as we know it is being redefined. I know that for most of us when we hear farming, the picture we have in our head is Old McDonald in his overalls driving around acres of land on a…


Are you’re wondering what those two words you keep hearing about mean, let’s talk about it.

What is Computer Vision?

Despite its complexity, computer vision is simply a computer’s ability to “see.” Computers, like humans, use sight to understand the world around them. They accomplish this differently than humans, but a lot of the principles are the same. For example, when you read “1 + 1” you know that this is a formula, and you should add one to one. In essence, you saw a pattern that you recognized and instantly knew how to interpret it. …

Kyle Kieser

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store