Artificial intelligence at MIT learned to train the neural network faster than ever


2019-03-23 11:45:06




1Like 0Dislike


In an attempt to "democratize the AI" scientists at mit have found a way to use artificial intelligence to much more effective learning systems machine learning — that is, neural networks. They hope that a new algorithm, which allows to save time and money, will allow resource-constrained researchers and companies to automate the design of neural networks. In other words, reducing the time and costs they could do this technique the AI more accessible.


neural network learn faster

A New field of artificial intelligence involves the use of algorithms for automatic design of neural networks that are more accurate and effective than those designed by human engineers. But this technology neuron-architectural search (neural architecture search NAS) is costly, in terms of processing power.

Most modern NAS algorithm, recently developed by Google to work on a bunch of GPUs, spent 48 000 GPU hours to create a single convolutional neural network used for image classification and detection tasks. Google has the ability to simultaneously run hundreds of GPUs and other specialized hardware in parallel, but is not available for many others.

The Algorithm of the NAS, presented the Massachusetts Institute of technology, can directly teach specialized convolutional neural network (CNN) for the target hardware platforms — working with a massive dataset of images is just over 200 GPU-hours, which significantly expands the potential use of these types of algorithms.

According to scientists, resource-constrained researchers and companies could benefit from the algorithm in the form of saving time and costs. The overall goal is "the democratization of AI," says study co-author song Han, associate Professor of electrical engineering and computer science Microsystems Technology Laboratories at MIT. "We want the experts on artificial intelligence and non-experts effectively designed the architecture of neural networks with a simple solution that quickly works on specific hardware".

However, he adds that such NAS algorithms will never replace engineers-people. "The goal is to get rid of repetitive and tedious work associated with designing and improving the architecture of neural networks".

Well, all this only accelerates the onset of General artificial intelligence. Speaking of Demis Hassabis, the founder — one of the most promising companies in the field of AI.


New method of water purification: as boiling, but much better

In most cases, drinking water without prior filtration and treatment it is impossible — it may contain hazardous microbes. Ways to get rid of them are numerous: from boiling and chlorination, to disinfect under the ultraviolet light, but researchers ...

Comments (0)

This article has no comment, be the first!

Add comment

Related News

The us Navy will receive in 2021 destroyer with a very powerful laser gun

naval forces of the United States are going to equip by 2021, one of their ships a powerful laser weapon. The installation, dubbed the High Energy Laser with Integrated Optical-dazzler and Surveillance (HELIOS), as reported by Pop...

Fish and bees learned to communicate with robots-interpreters

it's hard To believe, but two completely different species of fish and bees, learned to communicate with each other. Of course, this too loudly, but they really can share information with each other about their actions. It became ...

Scientists propose to treat alcoholism with laser brain stimulation

Anyone who has ever abused alcohol or cigarettes, he knows that to get rid of this kind of dependency is sometimes very difficult. Unfortunately, addiction to harmful substances while you can't just turn off one button, but resear...