The Office of Technology Licensing was established in 1970 to transfer technologies developed at Stanford. Find out more about OTL's history, mission, staff, and statistics.

Login to TechFinder » 

Reconfigurable Computing for Learning Bayesian Networks


Stanford Reference:

08-354


Abstract


Stanford researchers have designed a scalable Bayesian network learning algorithm and hardware platform that combines Bayesian learning and Markov Chain Monte Carlo sampling with supervised learning methods in a parallel design on reconfigurable hardware. This co-design of software and hardware allows for improved performance and quality of learning Bayesian networks and is scalable to networks with hundreds or thousands of variables.

Applications


  • Accelerates and improves learning and modeling of Bayesian networks

Advantages


  • Improves software performance by four orders of magnitude
  • Easily scalable to very large learning problems
  • Improved Quality and precision of learned models

Publications



Innovators & Portfolio



Patent Status



Date Released

 8/19/2013
 

Licensing Contact


Mona Wan, Associate Director
650-498-0902 (Business)
Login to Request Information

[-] Map/Timeline

93-173 All Fiber Polarization Splitting Switch
95-041 Polarized Unidirectional Superfluorescent Fiber Sources
95-048 Point-sink DNA Shearing Device

more technologies

Related Keywords


Bayesian analysis   signaling networks   signaling pathways   DNA analysis   Bayesian network   Computer vision   Signal processing   software: bioinformatics   dna sequencing   08-354   
 

   

  

Also of Interest...
93-173 All Fiber Polarization Splitting Switch
95-041 Polarized Unidirectional Superfluorescent Fiber Sources
95-048 Point-sink DNA Shearing Device

Recently Viewed...
S08-354 Reconfigurable Computing for Learning Bayesian Networks