PLDI 2019: New programming system ‘Gen’ developed for AI applications

Must Read

Howdy, Modi! : World media reactions on Modi-Trump’ grand Houston Event address

New Delhi, Sep 23: United States President Donald Trump and Indian Prime Minister Narendra Modi on late Sunday shared...

Howdy Modi : Modi-Trump mark history in US-India relationship with great show at Houston

Houston, Sep 22:  Modi, delivering his speech at the historic event, talks about the development underwent over five years...

ECI announces dates of Maharashtra & Haryana elections; Single Phase Election on October 21; Result on 24th

Election Commission of India has announced the dates of much-awaited state elections. According to the Chief Election Commissioner, Sunil...

New York, July 7 (IANS) Researchers have developed a novel system named “Gen” that can be used for Artificial Intelligence applications such as computer vision, robotics, and statistics without having to deal with equations or manually writing high-performance codes.

“Gen” includes a number of novel language constructs such as a generative function interface to encapsulate probabilistic models, combinators to create new generative functions from existing ones and an inference library providing high-level inference algorithms.

In the study published in the journal PLDI 2019, researchers from the Massachusetts Institute of Technology demonstrated the probabilistic programming system that aims to be both expressive at the modelling level and efficient at the algorithmic level.

“Gen” has already showed better performance than existing probabilistic programming systems for a number of different problems such as tracking objects in space, estimating 3D body pose from a depth image, and inferring the structure of a time series, researchers said.

Based on Julia – a language specialised in numerical analysis and which aims to allow users to express models and create inference algorithms using high-level programming constructs, “Gen” models can be expressed in a number of different ways, each striking a different flexibility/efficiency trade-off. “Gen” provides a built-in modelling language that extends Julia’s syntax for function definition.

“Gen” models are black boxes called generative functions (GF), that provide an interface (GFI), exposing capabilities required by inference, researchers said.

The generative function approach is key to making “Gen” suitable for application to a wide range of problems and enables it to use models created in TensorFlow as algorithms written in a programming language or as a result of simulations.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

- Advertisement -

Latest News

Nobel winner feels no grand theory can explain underdevelopment: Economists

By Sirshendu PanthKolkata, Oct 15 (IANS) Successful micro-level field experiments like the one that established a connect between barefoot...

Techie jumps to death from apartment in Hyderabad

Hyderabad, Oct 14 (IANS) A techie committed suicide by jumping from an apartment building in information technology cluster Gachibowli here on Monday, police said.P....

Jessica Alba: I’ve always been drawn to strong women

Los Angeles, Oct 15 (IANS) Actress Jessica Alba has always gravitated towards strong female characters, and says it is very important to represent complex...

Britain’s royal couple in Pakistan for 5-day visit

Islamabad, Oct 15 (IANS) Britain's Prince William, Duke of Cambridge, and Duchess of Cambridge, Catherine, arrived in Pakistan on a five-day visit, the Foreign...

Staff strike for wage revision grounds HAL operations (2nd Lead)

Bengaluru, Oct 14 (IANS) An indefinite strike by about 20,000 employees of the Hindustan Aeronautics Ltd (HAL) for wage revision on Monday grounded the...
- Advertisement -

More Articles Like This