Today we successfully tested one of our RS-25 engines, four of which will help power our Space Launch System (SLS) to deep space destinations, like Mars! This 500-second engine test concludes a summer of successful hot fire testing for flight controllers at our Stennis Space Center near Bay St. Louis, Mississippi.
The controller serves as the “brain” of the engine, communicating with SLS flight computers to ensure engines are performing at needed levels. The test marked another step toward the nation’s return to human deep-space exploration missions.
We launched a series of summer tests with a second flight controller unit hot fire at the end of May, then followed up with three additional tests. The flight controller tests are critical preparation for upcoming SLS flights to deep space– the uncrewed Exploration Mission-1 (EM-1), which will serve as the first flight for the new rocket carrying an uncrewed Orion spacecraft, and EM-2, which will transport a crew of astronauts aboard the Orion spacecraft.
Each SLS rocket is powered at launch by four RS-25 engines firing simultaneously and working in conjunction with a pair of solid rocket boosters. The engines generate a combined 2 million pounds of thrust at liftoff. With the boosters, total thrust at liftoff will exceed 8 million pounds!
Make sure to follow us on Tumblr for your regular dose of space: http://nasa.tumblr.com.
So if you’ve ever picked out paint, you know that every infinitesimally different shade of blue, beige, and gray has its own descriptive, attractive name. Tuscan sunrise, blushing pear, Tradewind, etc… There are in fact people who invent these names for a living. But given that the human eye can see millions of distinct colors, sooner or later we’re going to run out of good names. Can AI help?
For this experiment, I gave the neural network a list of about 7,700 Sherwin-Williams paint colors along with their RGB values. (RGB = red, green, and blue color values) Could the neural network learn to invent new paint colors and give them attractive names?
One way I have of checking on the neural network’s progress during training is to ask it to produce some output using the lowest-creativity setting. Then the neural network plays it safe, and we can get an idea of what it has learned for sure.
By the first checkpoint, the neural network has learned to produce valid RGB values - these are colors, all right, and you could technically paint your walls with them. It’s a little farther behind the curve on the names, although it does seem to be attempting a combination of the colors brown, blue, and gray.
By the second checkpoint, the neural network can properly spell green and gray. It doesn’t seem to actually know what color they are, however.
Let’s check in with what the more-creative setting is producing.
…oh, okay.
Later in the training process, the neural network is about as well-trained as it’s going to be (perhaps with different parameters, it could have done a bit better - a lot of neural network training involves choosing the right training parameters). By this point, it’s able to figure out some of the basic colors, like white, red, and grey:
Although not reliably.
In fact, looking at the neural network’s output as a whole, it is evident that:
The neural network really likes brown, beige, and grey.
The neural network has really really bad ideas for paint names.
For folks who have problems hearing, we updated the new video with closed captions (sorry for the holiday delay).
Me my entire life
Altmer: elves no-one likes including themselves
Bosmer: shapeshifting forest ninja elves with interesting culinary tastes
Dunmer: insect-riding, chain-smoking slaver elves
Orc: (former)elves no-one likes despite being awesome
Argonian: lizardmen who are the spawn of ancient god-like alien fungi trees
Khajiit: Cats. Also got so high they reached one of the moons
Imperial: the Roman Empire in a jungle. The jungle was retconned
Redguard: desert dwellers. May have literally sunk their previous continent with a massive spirit sword
Nord: buff dudes that can yell at problems to make them go away
Breton: half-elf, half-human, politicking, backstabbing witchmen who are always represented as boring generic medieval folks in all games
apparently i’m not enthusiastic enough about satan for google