Researchers are teaching machines to program themselves in an effort to write faster and more efficient software.

Researchers are teaching machines to program themselves in an effort to write faster and more efficient

Curated via Twitter from MIT Technology Review’s twitter account….

Working with a team from Intel, MIT and the Georgia Institute of Technology in Atlanta, he has developed a system called Machine Inferred Code Similarity, or MISIM, that can extract the meaning of a piece of code—what the code is telling the computer to do—in much the same way as natural-language processing (NLP) systems can read a paragraph written in English.

Microsoft is building basic code generation into its widely used software development tools, Facebook has made a system called Aroma that autocompletes small programs, and DeepMind has developed a neural network that can come up with more efficient versions of simple algorithms than those devised by humans.

MISIM is an exciting step forward, says Veselin Raychev, CTO at the Swiss-based company DeepCode, whose bug-catching tools—among the most advanced on the market—use neural networks trained on millions of programs to suggest improvements to coders as they write.

MISIM works by comparing snippets of code with millions of other programs it has already seen, taken from a large number of online repositories.

And as systems get more and more complex, tracking down these bugs gets more and more difficult. “It can sometimes take teams of coders days to fix a single bug,” says Justin Gottschlich, director of the machine programming research group at Intel.

MISIM can then suggest other ways the code might be written, offering corrections and ways to make it faster or more efficient.

Link to original article….

Leave a Reply

Leave a comment

Researchers are teaching machines to program themselves in an effort to write faster and more efficient software.

Researchers are teaching machines to program themselves in an effort to write faster and more efficient

Curated via Twitter from MIT Technology Review’s twitter account….

Working with a team from Intel, MIT and the Georgia Institute of Technology in Atlanta, he has developed a system called Machine Inferred Code Similarity, or MISIM, that can extract the meaning of a piece of code—what the code is telling the computer to do—in much the same way as natural-language processing (NLP) systems can read a paragraph written in English.

Microsoft is building basic code generation into its widely used software development tools, Facebook has made a system called Aroma that autocompletes small programs, and DeepMind has developed a neural network that can come up with more efficient versions of simple algorithms than those devised by humans.

MISIM is an exciting step forward, says Veselin Raychev, CTO at the Swiss-based company DeepCode, whose bug-catching tools—among the most advanced on the market—use neural networks trained on millions of programs to suggest improvements to coders as they write.

MISIM works by comparing snippets of code with millions of other programs it has already seen, taken from a large number of online repositories.

And as systems get more and more complex, tracking down these bugs gets more and more difficult. “It can sometimes take teams of coders days to fix a single bug,” says Justin Gottschlich, director of the machine programming research group at Intel.

MISIM can then suggest other ways the code might be written, offering corrections and ways to make it faster or more efficient.

Link to original article….

Leave a Reply

Leave a comment

Researchers are teaching machines to program themselves in an effort to write faster and more efficient software.

Researchers are teaching machines to program themselves in an effort to write faster and more efficient

Curated via Twitter from MIT Technology Review’s twitter account….

Working with a team from Intel, MIT and the Georgia Institute of Technology in Atlanta, he has developed a system called Machine Inferred Code Similarity, or MISIM, that can extract the meaning of a piece of code—what the code is telling the computer to do—in much the same way as natural-language processing (NLP) systems can read a paragraph written in English.

Microsoft is building basic code generation into its widely used software development tools, Facebook has made a system called Aroma that autocompletes small programs, and DeepMind has developed a neural network that can come up with more efficient versions of simple algorithms than those devised by humans.

MISIM is an exciting step forward, says Veselin Raychev, CTO at the Swiss-based company DeepCode, whose bug-catching tools—among the most advanced on the market—use neural networks trained on millions of programs to suggest improvements to coders as they write.

MISIM works by comparing snippets of code with millions of other programs it has already seen, taken from a large number of online repositories.

And as systems get more and more complex, tracking down these bugs gets more and more difficult. “It can sometimes take teams of coders days to fix a single bug,” says Justin Gottschlich, director of the machine programming research group at Intel.

MISIM can then suggest other ways the code might be written, offering corrections and ways to make it faster or more efficient.

Link to original article….

Related videos from YouTube

Leave a Reply

Leave a comment
%d bloggers like this:
scroll to top