The Power of Recurrent Neural Networks

Recurrent Neural Networks

A recurrent neural network (RNN) is a type of neural network where connections between units form a directed cycle. They were first created in the 1980s, but have gained new popularity as AI and machine learning technology is spreading and progressing across the planet into every industry and process. RNN’s are particularly good at dealing with issues like handwriting and image recognition, which require sequential understanding of data, because RNN’s are able to maintain information about a previous input. This technology has already been used to build on Natural Language Processing (NLP) to produce language models, for example, one such program input a huge number of Shakespeare’s poems, and after training these models they could generate their own “Shakespearean” poems that were almost indistinguishable from the originals!

A similar deep learning algorithm has now been written and successfully tested to describe any input image in a single sentence. This is a significant leap forward in terms of understanding how Machine Learning algorithms arrive at specific conclusions – the problem that scientists and engineers have been grappling with is the inability of AI (or any computer) to explain why it has arrived at the set of results or conclusions that it produced. Scientists at DARPA have been grappling with the problem for a while, but a recent paper has taken image recognition to the next level.

After images were fed into an RNN the algorithm was eventually able to produce a description of each image, including details that are not always obvious to machine learning algorithms (including the act of throwing a ball, as well as the concept of ‘over’ and ‘under’ – something that is notoriously difficult to ascertain from a 2D image). However, this RNN pattern and image recognition is only the beginning of what this technology can do – An even more recent paper has seen the technology careen forward at an incredible rate.

By using the feedback loops that are built into RNN’s sentences have been fed into a neural network, and brand new images have been synthesized from these descriptions. One network is used to create millions of images from the description, while a discriminator network is used to determine whether they match the description – as the program progresses the images become increasingly more accurate and refined as both neural networks work together to constantly improve and perfect their craft.

In a two stage version of this process the results were mind blowing – with the synthesized images going from blurred outlines to much higher quality images. While this technology is rather young and untested, the potential is almost unfathomable – what are currently 256×256 images could soon be HD pictures or animations. Eventually we could see entire novels illustrated or animated by this sort of algorithm – even see entire films played out simply by feeding in a detailed script and allowing the algorithm to do all the hard work.

One of the more abstract uses of deep learning

Google have predictably already been wrestling with the technology to produce synthesized images for their Google Street application. They have used RNN algorithms to produce new images by giving the algorithm an image from two other perspectives and asking the program to fill in the gaps and produce a brand new image. The idea is to create a seamless rolling movie on street view, rather than the disjointed experience that users currently experience when trying to explore streets on the other side of the world. So far they have been met with relative success, although being Google they have lamented the poor resolution quality of some of the more detailed aspects of each image.

This is one of the more abstract uses of deep learning, but it really shows us the wondrous untapped potential of this technology. It is going to infiltrate a revolutionise every single part of society, in ways that ewe can’t even begin to imagine. For now, we can just gaze in wonder at the powers of a few lines of code in Recurrent Neural Networks.

By Josh Hamilton

Hamza Seqqat

The Benefits of Virtualizing SD-WAN and Security

Benefits of Virtualizing SD-WAN As more companies adopt SD-WAN technology to enhance the agility of their networking architecture, they must give strong consideration to how and where to apply security across the network. There’s no ...
Mark Kirstein

IT Pros Can Now Deliver a More Streamlined, Cost-Efficient Migration of Microsoft Teams

IT Pros Deliver a More Streamlined Migration of Microsoft Teams In the modern workplace, the ability for employees to collaborate and engage with each other on projects in real time is becoming essential. The increased ...
Customers Will Recover From Downtime. But Will Your Business?

Customers Will Recover From Downtime. But Will Your Business?

Downtime Recovery Today’s society relies heavily on being connected to service providers. The ability of a business to transact or provide services online is now just as important as the products they offer, or the ...
Ramanan GV

Establishing a Unified Governance Model for the Digital Workforce

Increase visual control and reduce OPEX by 30% The Digital Service Providers (DSPs) are riding an automation wave. Painful manual tasks, which burdened staffs for ages, can now be easily handled by the software bots ...
Chris Collins

Why Cloud Technology is a Smart Business Move for Higher Education

Higher Education Technology Cloud technology is not just for the world of big business. A growing number of higher education institutions are also embracing the cloud’s many advantages, especially for its data gathering and analytics ...
David Friend

Cloud 2.0 will not be Ushered in by AWS or other Cloud Giants

Cloud 2.0 Trends Amazon, Google, and Microsoft are all pursuing similar business strategies: they want it all. ‘It,’ in this case, means the entire IT infrastructure in their cloud. Furthermore, they want you to buy ...