BNet.EngineKit™

Belief Networks are powerful modeling tools for condensing what is known about causes and effects into a compact network of probabilities. BNet® is a family of tools for building, using and embedding belief networks in your own software.

  • BNet.Builder™ - to rapidly create Belief Networks, enter information, and get results
  • BNet.EngineKit - to incorporate Belief Network technology into applications

Spend your time being an expert in your field, not becoming an expert in Bayesian Networks.

BNet.EngineKit is a developer toolkit for researchers and engineers to use to embed belief networks in software applications. Unique in its focus on clear APIs with the right functionality, BNet.EngineKit offers software developers who aren’t inference algorithm specialists a chance to use Bayesian networks without spending years learning about them.

BNet.EngineKit includes:

  • Clear, concise documentation – to get you to implementation quickly
  • Beliefs & Evidence Tools – Building the code to get beliefs out and enter evidence into a network are the most common and most time consuming tasks in building applications that use belief networks.
  • Fast Inference – Charles River Analytics’ proprietary inference engine, available only in BNet products, is one of the fastest belief network inference engines available
  • Learning - BNet.EngineKit can learn your CPTs from data in both fully and partially observed Bayesian networks.
  • Multithreading Support – Thread-compatible engine and documentation to help you implement multithreading in your projects

With BNet.EngineKit’s utilities, documents and sample code, you can implement your belief networks in your projects easily and simply, and make a difference with your work quickly. Read on for more details.

 

Documentation

Clear, concise documentation for quick implementation

  • Developer Manual with example implementations and sample code – including:
    • High-level summaries and descriptions of available functions
    • Activity-based examples with sample code
  • Detailed Javadocs with instructions on the nuts and bolts making code work

Beliefs & Evidence Tools

Building the code to get beliefs out and enter evidence into a network are the most common and most time consuming tasks in building applications that use belief networks. Speed up your implementation with:

  • Belief Alerts:
    • Automated notification when beliefs at any node are updated
    • Alerts that can be set to trigger on a wide variety of node conditions, including belief thresholds and ranges, node names, state names and more
  • Evidence Discretizer set ranges to convert continuous variables into hard evidence
  • Evidence Fuzzifier set ranges to convert continuous variables into soft evidence
  • Utility Methods for common tasks like getting evidence and beliefs, posting evidence, and more

Fast Inference

Charles River Analytics’ proprietary inference engine, available only in BNet products, is one of the fastest belief network inference engines available.

Learning 

BNet.EngineKit can learn your CPTs from data in both fully and partially observed Bayesian networks.

Multithreading Support

Thread-compatible engine and documentation help you implement multithreading in your projects.

 


 

System Requirements

  • Windows operating system; any Java-enabled platform (Java 1.4 or higher)
  • 1.5 GHz processor
  • 256 MB RAM
  • 40 MB hard-drive space
  • Internet connection for receiving updates (optional)

Note:  the processor speed and memory capacity specified above areonly recommended values, not minimum required values. BNet.EngineKit should work well for most networks with the above processor speedand memory capacity. Slower processor speed and smaller memory capacity will result in degraded performance. Faster processor speed and larger memory capacity will increase performance of BNet.EngineKit and allow for larger network size. 

Additional Technical Specifications

 

Product Licenses

  • BNet.EngineKit 1.0 - $5,000.00*

To purchase a license, contact us.

 

Support

Support for BNet.EngineKit is available through our Support Package.

The BNet.EngineKit Support Package provides:

  • Access to technical support via email
  • Response within 1 business day
  • Priority on routine requests (such as re-installation and upgrades)
  • Access to Beta version Products, allowing you and your organization
    • Insight into coming product releases
    • A chance to influence product development
  • 10% discount on training and consulting
  • On-site visits at an affordable rate
 
BNet.EngineKit Support (1 year) - $1,250.00*
 
BNet Support Agreement

To order the BNet.EngineKit Support package, contact us.

 

Training

1-day introductory courses for using BNet.EngineKit are available. For schedules and prices, please contact us.

 

Trial Download

Click here to download a trial version.

Continuing with download indicates acceptance of our license agreement.

 

Prices exclude European V.A.T., local sales taxes, import duty if any, and postage. Prices are subject to changes without further notice.

 

Close
Contact Us