machine learning - AI Weirdness

This neural net makes my sketches real

By Janelle Shane On June 15, 2019 - 4 min read

There’s a kind of neural net that will convert block drawings into its best attempt at a photorealistic scene. Now it’s easier than ever to try them out, without any coding or fancy computing equipment needed. Today I’m going to show you an algorithm developed by Nvidia

Learning to hack like a faulty AI

By Janelle Shane On April 26, 2019 - 3 min read

So last week I was a biiiit busy, traveling to Vancouver to give a TED talk(!!!!). I’ll post the talk when it goes live online, probably at the end of October. For me, one of the highlights of the 2019 TED conference was Simone Giertz’s “Sh*tty Robot

Training an AI assistant

By Janelle Shane On January 11, 2019 - 3 min read

There’s an adorable game called Lab Assistant [https://lizfiacco.itch.io/lab-assistant], in which you get to train a machine learning algorithm to obey your commands. Sadly, the commands don’t include “make me a sundae” or “wield this sword of justice”, but it turns out you can learn

Why did the neural network cross the road?

By Janelle Shane On June 08, 2018 - 3 min read

Can a machine learning algorithm learn to tell a joke? I’ve experimented with neural networks and jokes before, teaching them to tell knock-knock jokes [http://aiweirdness.com/post/159132506927/in-which-a-neural-network-learns-to-tell] , or to generate April Fools pranks [http://aiweirdness.com/post/172345256807/april-fools-pranks-written-by-neural-network] . In each case, the results were… underwhelming.

NFL draft picks, as described by a neural network

By Janelle Shane On April 26, 2018 - 2 min read

Every year the NFL recruits new football players in a process known as the NFL Draft. Scouts watch the prospective players, and the NFL posts their lists of each player’s strengths and weaknesses [https://www.nfl.com/draft/tracker/prospects/allPositions?college=allColleges&page=1&status=ALL]

When algorithms surprise us

By Janelle Shane On April 13, 2018 - 5 min read

Machine learning algorithms are not like other computer programs. In the usual sort of programming, a human programmer tells the computer exactly what to do. In machine learning, the human programmer merely gives the algorithm the problem to be solved, and through trial-and-error the algorithm has to figure out how

Ten new applications for neural networks

By Janelle Shane On December 28, 2017 - 3 min read

Neural networks are machine learning algorithms that are very good at solving tough problems - they’re used for language translation, facial recognition, and financial management. I, however, have been training them on silly datasets. Here are some of my favorite experiments from the last year. Naming guinea pigs [http:

The neural network generated pickup lines that are actually kind of adorable

By Janelle Shane On April 07, 2017 - 1 min read

So it occurred to me that the same neural network framework [https://github.com/karpathy/char-rnn] I’ve trained on recipes [http://lewisandquark.tumblr.com/post/140219420017/the-silicon-gourmet-training-a-neural-network-to] , Pokemon [http://lewisandquark.tumblr.com/post/159027130687/pokemon-generated-by-neural-network] , superhero names [http://lewisandquark.tumblr.com/post/140829108357/superheroes-designed-by-neural-network] , and Irish tune names [http:

Delicious recipe titles generated by neural network

By Janelle Shane On April 01, 2017 - 1 min read

I’ve been training a neural network (based on this open-source neural network framework from Andrej Karpathy [http://t.umblr.com/redirect?z=https%3A%2F%2Fgithub.com%2Fkarpathy%2Fchar-rnn&t=NDVkOGIwZmQ4NzM1ZjIxMTcwOGFhN2RjZjBlZjYyMjgzN2M5MzJmYyx2Q0pORUpRbQ%3D%3D&b=t%3AIinBpZOgiMHH_bphj7hrOQ&p=http%3A%2F%2Flewisandquark.tumblr.com%2Fpost%2F159062141927%

Three bad recipes generated by neural network

By Janelle Shane On March 30, 2017 - 1 min read

I’m training a neural network to generate recipes [http://lewisandquark.tumblr.com/post/140219420017/the-silicon-gourmet-training-a-neural-network-to] based on a database of about 30,000 examples, and although the network has managed to produce identifiable recipes, and even sometimes sort sweet from savory, it hasn’t actually managed to produce any

Tag: machine learning

This neural net makes my sketches real

Learning to hack like a faulty AI

Training an AI assistant

Why did the neural network cross the road?

NFL draft picks, as described by a neural network

When algorithms surprise us

Ten new applications for neural networks

The neural network generated pickup lines that are actually kind of adorable

Delicious recipe titles generated by neural network

Three bad recipes generated by neural network

Writing

Subscribe

Recent Posts

Minecraft with object impermanence

Bonus: In Which The Adventurer Attempts to Build a Website

Botober 2024

Bonus: "Ignore all previous instructions" gets weirder

An exercise in frustration

Bonus: A unicorn goes downhill

Follow

Minecraft with object impermanence

Bonus: In Which The Adventurer Attempts to Build a Website

Botober 2024