MACHINE LEARNING

Machine learning is concerned with the design and development of algorithms that allow computers to evolve behaviors based on empirical data, such as from sensor data or databases. A learner can take advantage of examples (data) to capture characteristics of interest of their unknown underlying probability distribution. Data can be seen as examples that illustrate relations between observed variables. A major focus of machine learning research is to automatically learn to recognize complex patterns and make intelligent decisions based on data; the difficulty lies in the fact that the set of all possible behaviors given all possible inputs is too large to be covered by the set of observed examples (training data). Hence the learner must generalize from the given examples, so as to be able to produce a useful output in new cases.

Applications for machine learning include machine perception, computer vision, natural language processing, syntactic pattern recognition, search engines, medical diagnosis, bioinformatics, brain-machine interfaces and cheminformatics, detecting credit card fraud, stock market analysis, classifying DNA sequences, speech and handwriting recognition, object recognition in computer vision, game playing, software engineering, adaptive websites, robot locomotion, and structural health monitoring.

Special computers and hardware accelerators have been proposed to do some kind of processing of Boolean functions: evaluation, such Boolean operations as intersection or complementation, checking for tautology or satisfiability, verification, resolution, etc., since all NP-complete problems can be reduced to one of the above problems and particularly to the 3-SAT Problem. Multiple-valued logic, along with a general problem-solving methodology, can be used to reduce any problem to some consistent labeling problem and next reducing it to some manipulations of multiple-valued logic functions.

FPGA-based hardware accelerators of certain machine learning algorithms have shown 10,000x performance improvement over software methods. Omnibase Logic is extending these methods into silicon implementations using SUS-LOC to achieve even further improvements and scalability beyond the limits of current FPGA technology.