Plausible Neural Networks (PNN) Technologies

Plausible Neural Networks (PNN) is designed for the next generation of intelligent computing machines. PNN has several innovative breakthrough technologies, which are under US and PCT patents. PNN employs parallel distributed processing that is currently implemented by cluster computing on cloud platforms.  In the future, PNN can be implemented by neuromorphic circuits and other kinds of physical computing systems.

In the era of Industries 4.0, machine intelligence will be the forefront of new technologies. Beside Big Data Analytics, PNN can be applied to the Internet of Thing (IOT), Autonomous Robots, Intelligence Maintenance, and other Cyber Physical Systems. We welcome collaborating in Research & Development in all of these areas.

robot mendicitintegrated microchip

Features

  • Self-organization

    PNN learning is entirely unsupervised, based on competitive neuronal signals for entropy reduction.

  • Fast learning algorithms

    PNN has the fastest learning algorithm among the current neural network and machine learning methods.

  • Universal data analysis

     PNN performs clustering, classification, function estimation, associative memory and statistical inference.

  • Parallel distributed processing

    PNN employs parallel and distributed computing for large scale data analysis.

  • Cloud computing

    PNN employs learning and data analysis on cloud platforms.

  • Multi-resolution cluster analysis

     PNN organizes coarse and detail pattern profiles by different network levels.

  • High dimensional model

    PNN builds large scale high dimensional models from data.

  • Knowledge extraction and inference rules

    PNN extracts knowledge and rules for the relationships between variables through network queries.