iAbra Neural Pathworks

iAbra Neural Pathworks

iAbra delivers a best-in-class, end-to-end enterprise neural network creation platform. Pathworks toolkit provides all the integrated components you need to go from example data to high-performance, low latency, low power inference. Neural Pathworks runs on Intel Xeon based server with an attached Intel FPGA to ensure the neural network runs consistently in deployment. The tool enables users to provide an annotated data set, or to add annotations to a data set, and will then automatically search the design space for the optimum neural network, abstracting away the complexity of programming, building, and hand-tuning of neural networks for FPGAs.

*Please note that member solutions are often customizable to meet the needs of individual enterprise end users.



  • User Interface
    A web based user interface ensures both ease of access and an intuitive process. The interface abstracts the complexity of the required data and computer science to create a unique neural network from data.
  • Data Preparation
    The data used to train an FPGA specific neural network is prepared within PathWorks, enabling the high signal to noise masking and annotation necessary.
  • Evolutionary Architecture
    iAbra leverages scalable High Performance Computing infrastructure and the underlying principles of machine learning to automate the process.
  • HPC Integration
    PathWorks provides the integration to and management of an integrated system negating the need for additional hardware tools.
  • Machine Learning Algorithm
    The trained neural network is required to be small and highly efficient in order to fit within the FPGA fabric. iAbra’s learning algorithm targets specific FPGA silicon for inference.
  • Precompiled Output
    The neural networks created by PathWorks can be compared, and those with the greatest efficacy selected to be compiled to FPGA hardware for an embedded design.



WorldwideAI Software/SaaSCross-IndustryDefense and SpaceHealthcareAnomaly DetectionImage/Object Detection/Recognition/ClassificationSmart CityHybrid CloudOn-premise (Private Cloud, Other)Intel® Xeon® Scalable ProcessorIntel® Core™ ProcessorIntel Atom™ ProcessorIntel® FPGAModels cant be re-trained - Inference onlyLinux ProprietaryDeep Learning