Neural Vision System :: Essays Papers

Neural Vision SystemResearchers at the University of Houston in Texas match developed a neural vision system that allows a automaton to adapt to a changing domain of a function. The machine is designed to explore, contract (for recrudesce or worse) and then make future decisions found on that experience typical behavior for any neural device. What is unusual is its ability to learn new tricks if the rules it learned through experience no longer apply. In both simulated and hardw be experiments, the robot was shown to be able to separate objects correctly, even if the value associated with them changed over time. Neural webs are computing devices base on the way our own brains work. They consist of many, usually simple, processing elements that are wired together in parallel. Unlike conventional computers, which are based on algorithms or rules to be followed in order to produce a result, neural networks act as adaptive filters. They are trained by feeding them inputs and t he correct answers to those inputs. This information changes the way the network is connected so that the next connatural input can produce a similar correct output. One of the issues that neural network designers have been struggling with over the years is how to structure the neural network without prejudging the situations that it is going to encounter. Other methods of creating near intelligence, such as building in so-called behaviors or creating dependable systems, have the disadvantage of generally requiring some fellowship about the world before they start. In behavioral robots (those that have an automatic, preprogrammed response to stimuli from the outside world), that companionship can be hard wired, whereas, in the expert system case, the knowledge is contained in the software. Engineers Ramkrishna Prakash and Haluk gmen wanted, instead, for their robot to be able to learn on the go away the way people do, adapting as circumstances changed. The solution they came up with is the neural-network architecture, called frontal. Basically, the network allows a robot (in this case a robot arm with boob tube cameras for eyes) to identify new objects and decide whether to pick them up, and learn from its previous obedient and bad decisions. The first part of the system (labeled spatial novelty) is an array of so-called gated dipoles, each of which addresses a different area in the robots field of view. The gated dipoles essentially performs a comparison between the incoming information about that orchestrate in space and what it was like previously.