A Robot Scientist Will Dream Up New Materials To Advance Computing (technologyreview.com) 41
An anonymous reader quotes a report from MIT Technology Review: In a laboratory that overlooks a busy shopping street in Cambridge, Massachusetts, a robot is attempting to create new materials. A robot arm dips a pipette into a dish and transfers a tiny amount of bright liquid into one of many receptacles sitting in front of another machine. When all the samples are ready, the second machine tests their optical properties, and the results are fed to a computer that controls the arm. Software analyzes the results of these experiments, formulates a few hypotheses, and then starts the process over again. Humans are barely required.
The setup, developed by a startup called Kebotix, hints at how machine learning and robotic automation may be poised to revolutionize materials science in coming years. The company believes it may find new compounds that could, among other things, absorb pollution, combat drug-resistant fungal infections, and serve as more efficient optoelectronic components. The company's software learns from 3-D models of molecules with known properties. Kebotix uses several machine-learning methods to design novel chemical compounds. The company feeds molecular models of compounds with desirable properties into a type of neural network that learns a statistical representation of those properties. This algorithm can then come up with new examples that fit the same model. To strain out potentially useless materials, Kebotix uses another neural network and "then the company's robotic system tests the remaining chemical structures," reports MIT Technology Review. "The results of those experiments can be fed back into the machine-learning pipeline, helping it get closer to the desired chemical properties. The company dubs the overall system a 'self-driving lab.'"
The setup, developed by a startup called Kebotix, hints at how machine learning and robotic automation may be poised to revolutionize materials science in coming years. The company believes it may find new compounds that could, among other things, absorb pollution, combat drug-resistant fungal infections, and serve as more efficient optoelectronic components. The company's software learns from 3-D models of molecules with known properties. Kebotix uses several machine-learning methods to design novel chemical compounds. The company feeds molecular models of compounds with desirable properties into a type of neural network that learns a statistical representation of those properties. This algorithm can then come up with new examples that fit the same model. To strain out potentially useless materials, Kebotix uses another neural network and "then the company's robotic system tests the remaining chemical structures," reports MIT Technology Review. "The results of those experiments can be fed back into the machine-learning pipeline, helping it get closer to the desired chemical properties. The company dubs the overall system a 'self-driving lab.'"
Won't work, I've already tried this. (Score:3)
Re: I thought computer operated systems like this. (Score:2)
Feel free to start your own robot lab and give away the results for free.
Reminded me of this: (Score:2)
The infinite monkey theorem states that a monkey hitting keys at random on a typewriter keyboard for an infinite amount of time will almost surely type a given text, such as the complete works of William Shakespeare. In fact, the monkey would almost surely type every possible finite text an infinite number of times.
Re: (Score:3)
Except that they're not trying random things. Search is directed by neural network.
Itâ(TM)s not the first (Score:2)
No insight possible (Score:2)
Re: No insight possible (Score:2)
It still is.
Dream up? (Score:2)
Robots don't dream -- there are no brainwaves. Either it is trying materials at random or enumerating the permutations.
Who the fuck writes this garbage?
function DreamUp()
{
return Math.floor(Math.random() * NUM_MATERIALS);
}
Re: (Score:1)
Pretty much this. Its basically taking the place of undergraduates. Go and mix this and that together and see what happens. The upside of having a robot do it is that you don't have that pesky problem of undergrads poisoning themselves when they mix the wrong chemicals together.
Re: (Score:2)
xkcd [xkcd.com] says your function is too complex.
Re: (Score:2)
Haha, yeah I was debating whether to include that PS4 satire or not.
We've seen how this turns out (Score:1)
Mugshots (Score:2)