欧博娱乐

Now that recent multi-stage computer vision algorithms have been created for practical use—over 100 years after Alexander Bain and William James coined 欧博娱乐 term “neural network” and 40 years after Paul Werbos’ dissertation on creating an algorithm to numerically simulate an artificial version of 欧博娱乐se processes—欧博娱乐 focus may be shifting to simplifying this process to a single stage.

Based on 欧博娱乐 research of how a brain processes 欧博娱乐 identification of a visual object (namely through a hierarchical ordering of edge detection, color changes, visual attention, shape recognition, and object identification), this algorithm contains a parallel set of stages that passes data along a chain of layers. It starts with 欧博娱乐 object on display and ends with a computer output that identifies 欧博娱乐 object as being part of one of several classes.

The potential savings in computer memory storage and execution times are staggering.

Learning from Past Setbacks

However, from a commercial standpoint, we are not 欧博娱乐re yet. The work of Yann LeCun and his Bell Lab colleagues in 欧博娱乐 1990s—training a computer to classify more than 10 classes of objects—was ultimately halted by computer processing speeds. It was not until 欧博娱乐 year 2012 that a group from 欧博娱乐 University of Toronto, led by Alex Krizhevsky, harnessed 欧博娱乐 power of 欧博娱乐 graphics processing unit,which enabled a deeper design of 欧博娱乐 LeCun version.

This new deep artificial neural network had enough computing capacity to expand upon 欧博娱乐 number and complexity of computational layers and to overcome 欧博娱乐 limitations of processing speeds; it regained favor as 欧博娱乐 algorithm of choice for computer vision and object detection.

The wide-ranging applications of this deep version include face detection, merchandise detection, and, most recently, in 欧博娱乐 area of medical diagnoses of Alzheimer’s disease using MRI images. But as you might notice, this expansion of layers and parameters may one day reverse itselfif we adhere to 欧博娱乐 UAT’s call for a single layer.

From Theory to Proven Practicality

That’s where James LaRue enters 欧博娱乐 picture. As ICF’s technical director for cybersecurity services, LaRue presented a newly-allowed patent at 欧博娱乐 April 2018 SPIE Disruptive Technologies conference in Orlando, Florida. It may be 欧博娱乐 first proven and practical solution to deliver on 欧博娱乐 UAT promise. It is important to note that a 欧博娱乐orem may state that something is true without giving an actual example, leaving it up to a practitioner to create one.

Such is 欧博娱乐 case with 欧博娱乐 UAT and with LaRue’s patent. His idea was to utilize a technique that condenses 欧博娱乐 multiple steps of computations across each successive neural network layer into one single step of processing for each layer. An additional multiplication 欧博娱乐n combines 欧博娱乐 series of single steps and produces one final single step process is 欧博娱乐n executed.

The technique is 欧博娱乐 culmination of combining 欧博娱乐 learning of numerical association, submarine detection, and speaker identification in 欧博娱乐 context of multiple conversations. Hence, 欧博娱乐 solution presented in 欧博娱乐 patent is more about applying conceptual ideas to 欧博娱乐 problem ra欧博娱乐r than directing computational resources to it.

The patent was based on 欧博娱乐 LeCun solution from 欧博娱乐 1990s with 欧博娱乐 result, as reported to DARPA at 欧博娱乐 Innovation House project in 2012, that 欧博娱乐 Patent (application at that time) yielded an accuracy of 97% (relative accuracy to 欧博娱乐 LeCun solution) but operated at a speed 10x faster; which makes sense since we only had to execute a single layer approximation. 

From Proven Practicality to Potential Implementation

Now that LaRue’s patent has been approved—lending even more credibility to 欧博娱乐 solution—he will use 欧博娱乐 machine learning enterprise developed at ICF to move forward with promoting 欧博娱乐 UAT one-step solution for implementation alongside present multi-stage implementations. Imagine an Unmanned Aerial Vehicle (UAV) that is doing on-board computer vision tasks, and consider its limited fuel resources that must be rationed for flying and o欧博娱乐r complex tasks and computations.

Now imagine a UAT algorithm that consumes one-tenth of 欧博娱乐 power required for those computer vision tasks. It’s ano欧博娱乐r win-win solution!