DeepCoder solves coding programming challenges by ripping of existing codes.
As each day passes by, Artificial Intelligence is getting smarter. A new AI program has now gained the ability to write its own code.
The AI program, which is built by Microsoft and Cambridge University researchers, is able to solve programming problems — by stealing code from other programs. The system called DeepCoder, has the ability to solve basic programming challenges by plagiarizing bits of code from other existing software.
To solve these programming problems, and write code, the machine uses a technique known as program synthesis - can be used to automate the tedious part of code development and let the developers focus on complex tasks.
The most wonderful outcome of this machine is that it will give people the ability to build programs, without knowing how to code. Reported by New Scientist, the system is said to take lines of code from existing programs and combining them respectively.
Researchers wrote in the paper, “We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to predict properties of the program that generated the outputs from the inputs."
This neural network can also take design clues and develop a program after harvesting appropriate lines of code from a massive code database using machine learning. It is said to analyze which lines would be the best fit and writes a working code, in just a few seconds. At the moment, DeepCoder is only capable of solving programming challenges that involve around five lines of code.
“We use the neural network’s predictions to augment search techniques from the programming languages community, including enumerative search and an SMT-based solver. Empirically, we show that our approach leads to an order of magnitude speedup over the strong non-augmented baselines and a Recurrent Neural Network approach, and that we are able to solve problems of difficulty comparable to the simplest problems on programming competition websites.” Building an AI which is capable of such intense coding could soon, revolutionize the development of computer programs.
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
 "DeepCoder, Google, Artificial Intelligence, Microsoft, University of Cambridge, Web Exclusive, program synthesis, coding, coding")
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}
)
){kind=small}
){kind=small}
)
)
)
)
)
){kind=small}
){kind=small}
){kind=small}
){kind=small}
){kind=small}