machine learning

1 posts
How artificial intelligence can augment our own

There’s another essay on Distill by Shan Carter and Michael Nielsen. They describe and demonstrate how one might use artificial intelligence to augment human intelligence. Our essay begins with a survey of recent technical work hinting at artificial intelligence augmentation, including work on generative interfaces – that is, interfaces which can be used to explore and visualize generative machine learning models. Such interfaces develop a kind of cartography of generative...

0 0
Machine learning demo with your webcam and GIFs

The Teachable Machine from Støj, Use All Five, and Google is a fun experiment that lets you “teach” your computer. Your webcam is used as an input device, and using deeplearn.js, you can make three classifications that change the output. Use different hand gestures, faces, or movements to signal differences, and you can see probabilities change in real-time. It’s hard to believe this stuff runs so smoothly in the browser...

0 0
Machine learning to find spy planes

Last year, BuzzFeed News went looking for surveillance flight paths from the FBI and Homeland Security. Peter Aldhous describes how they did it. They used machine learning — a random forest algorithm to be more specific — to find the spy planes, which as you might expect tended to circle around more than normal flights. Tags: BuzzFeed, flights, machine learning

0 0
Minimizing discrimination in machine learning

From Google Research, a look at how discrimination in machine learning can lead to poor results and what might be done to combat: Here we discuss “threshold classifiers,” a part of some machine learning systems that is critical to issues of discrimination. A threshold classifier essentially makes a yes/no decision, putting things in one category or another. We look at how these classifiers work, ways they can potentially be unfair,...

0 0
Visual collection of bird sounds

Different species of birds make different sounds. However, the sounds are so quick and compressed that it can be tough to pick out what is what. So Kyle McDonald, Manny Tan, and Yotam Mann created a “fingerprint” for each bird song and used machine learning to classify. Through the visual browser, you can play sounds and search for bird types. Similar sounds are closer to each other. Tags: birds, Google,...

0 0
Visual connections between art pieces

This is neat. A Google Arts & Culture Experiment, X Degrees of Separation shows a path of visual connections between two art pieces of your choosing. It’s like Six Degrees of Kevin Bacon but with art, computer vision, and machine learning. Tags: art, Google, machine learning, vision

0 0
Deep fried data

Maciej Ceglowski, the creator of bookmarking site Pinboard, spoke at the Library of Congress a couple of weeks ago about deep-fried data. In our case, the deep-fryer is a toolbox of statistical techniques. The names keep changing—it used to be unsupervised learning, now it’s called big data or deep learning or AI. Next year it will be called something else. But the core ideas don’t change. You train a computer...

0 0
Sci-Fi short film scripted by machine learning algorithm

Filmmaker Oscar Sharp and technologist Ross Goodwin fed a machine learning algorithm with a bunch of Sci-Fi movie scripts to see what new script it would spit out. A script for Sunspring is the result, and this is the film, starring Thomas Middleditch. Riveting. x The thought of a machine tapping into emotion and creativity likely brings some sneers, but Goodwin argues that it’s about assistance and augmentation rather than...

0 0
Visual introduction to machine learning

What is machine learning? It sounds like a bunch of computers get together in the library on Tuesdays and study during all-nighters. It's not quite that. Stephanie Yee and Tony Chu provide a really good visual explanation of the computer science subfield. The vertical scroller should clear up some misconceptions. The great thing about it is that it walks you through a basic example and shows you step-by-step what's actually...

0 0
Automated Super Mario World gameplay through machine learning

Seth Bling made a bot — MarI/O — that automatically learns how to play Super Mario World. It's based on research by Kenneth O. Stanley and Risto Miikkulainen from 2002 that uses neural networks that evolve with a genetic algorithm. MarI/O starts out really dumb, just standing in place, but after enough simulations it get smart enough to navigate the world. Code available here and the paper from Stanley and...

0 0