Market News

Theatre

Advert

ad
11 Dec 2017

Neural networks translation breakthrough made at MIT

MIT researchers have found that changing the way neural networks look at data makes them better at understanding languages.

Researchers discovered that by applying a recently developed interpretative technique, they could analyse neural networks and assess the way they work.

What they found is that the systems typically concentrated on lower-level tasks, such as sound recognition, before moving onto higher-level tasks, like understanding the nuances of sentences and different ways they could be interpreted.

Neural networks

Importantly, the researchers also found that while carrying out this process, the systems were choosing not to assess a certain type of data. Once told to include this, the systems improved.

Though the performance improvement was relatively small, it is significant because it shows that analysing the way neural networks carry out tasks can help improve artificial intelligence systems.

MIT: MIT researchers use AI-based system to see round corners

Artificial intelligence: UK government makes AI key part of industrial strategy

Jim Glass, a senior research scientist at CSAIL, the MIT department that carried out the research, said: “In machine translation, historically, there was sort of a pyramid with different layers.

“At the lowest level, there was the word, the surface forms, and the top of the pyramid was some kind of interlingual representation, and you’d have different layers where you were doing syntax, semantics.

“This was a very abstract notion, but the idea was the higher up you went in the pyramid, the easier it would be to translate to a new language, and then you’d go down again. So, part of what we’re doing is trying to figure out what aspects of this notion are being encoded in the network.”

Neural networks analyse very large sets of data in order to learn how to perform tasks and have been a key part of the development of artificial intelligence, particularly in areas like speech-recognition and translation.

But fully understanding the way they work has been a challenge for some time. When a network trains itself to perform a task, it adjusts its internal settings in an unpredictable way. This study has had some success in this, alongside its developments in AI.

Click here to read more.

View all Market News
Loading

Sponsors

Diamond Sponsor

Platinum Sponsors

 

VIP Lounge Sponsor

Theatre Sponsors

She Loves Data Live Sponsors

Gold Sponsors

 

Gold Sponsors

 

Gold Sponsors

 

Silver Sponsors

Silver Sponsors

Silver Sponsors

 

Silver Sponsors

Silver Sponsors

Silver Sponsors

Bronze Sponsors

Bronze Sponsors

Bronze Sponsor

Bronze Sponsors

Bronze Sponsors

Bronze Sponsors

Partners

Knowledge Partner

News Distribution Partner

Associate Content Partner

Strategic SEO Partner

She Loves Data Live! Partners

She Loves Data Live! Partners

She Loves Data Live! Partners

She Loves Data Live! Partners

Event Partners

Event Partners

Event Partners

Event Partners

Event Partners

Event Partners

Media Partners

Media Partners

Media Partners

Media Partners

Media Partners

Media Partners

Media Partners

Official Partner Hotel

Testimonials

  • "We are impressed with the sheer volume of crowd visiting our booth. We’ve had very good interactions with the delegates and alliance partners."
    Marketing Director, TIBCO Software
  • "We’ve met a good mix of new prospects and existing customers over the two days. There were many relevant questions posed by the delegates, attesting to the immense interest the show has generated for us leading up to the show."
    Marketing – South East Asia and India, Splunk
  • "The conversations in the big data community around machine learning is a lot more mature here. Not only the delegates are interested in big data, they are also keen to learn more about data science, artificial intelligence and internet of things."
    Regional Sales Director, Qubole Inc.
  • "I’m amazed with the diversity of vendors from data centre, big data, data integrators and cloud solution providers. There’s something here for almost anybody from the technology world. The most valuable takeaway for me is the opportunity to meet with our technology partners, alliance partners as well as our prospect and existing customers.!
    Head of Cloud Sales, Talend