May 25, 2022

7 Posts

Driver one passing driver two who has no gas
May 25, 2022

Linear Regression: Straight & Narrow

Linear regression may be the key statistical method in machine learning, but it didn’t get to be that way without a fight. Two eminent mathematicians claimed credit for it, and 200 years later the matter remains unresolved. The longstanding

3 min read
Andrew Ng staring at neural networks
May 25, 2022

Special Issue! Foundational Algorithms, Where They Came From, Where They're Going

Years ago, I had to choose between a neural network and a decision tree learning algorithm. It was necessary to pick an efficient one, because we planned to apply the algorithm to a very large set of users on a limited compute budget. I went

17 min read
K-Means Clustering: Group Think
May 25, 2022

K-Means Clustering: Group Think

If you’re standing close to others at a party, it’s likely that you have something in common. This is the idea behind using k-means clustering to split data points into groups. Whether the groups formed via human agency or some other force, this

3 min read
Man sitting on a tree with a monkey and a gorilla
May 25, 2022

Decision Trees: From Root to Leaves

What kind of beast was Aristotle? The philosopher's follower Porphyry, who lived in Syria during the third century, came up with a logical way to answer the question. He organized Aristotle’s proposed “categories of being” from general to

3 min read
Neural Networks: Find the Function
May 25, 2022

Neural Networks: Find the Function

Let’s get this out of the way: A brain is not a cluster of graphics processing units, and if it were, it would run software far more complex than the typical artificial neural network. Yet neural networks were inspired by the brain’s architecture:

3 min read
Two people rock climbing
May 25, 2022

Gradient Descent: It’s All Downhill

Imagine hiking in the mountains past dusk and finding that you can’t see much beyond your feet. And your phone’s battery died so you can’t use a GPS app to find your way home. You might find the quickest path down via gradient descent. Just

3 min read
Two people drinking danger poison
May 25, 2022

Logistic Regression: Follow the Curve

There was a moment when logistic regression was used to classify just one thing: If you drink a vial of poison, are you likely to be labeled “living” or “deceased”? Times have changed, and today not only does calling emergency services provide a better

2 min read

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox