Industrial Research And Consultancy Centre
PrxCa1-xMnO3 based Stochastic Neuron for Boltzmann Machine to Solve “Maximum Cut" Problem
Abstract

This invention presents an approach to solve complex computational problems, specifically focusing on the "Maximum Cut" problem. By leveraging a novel PrxCa1-xMnO3-based Stochastic Neuron for Boltzmann Machine (BM), the system introduces a new paradigm for tackling NP Hard problems, which have wide-ranging practical implications. The design incorporates analog and digital components to create a stochastic neuron capable of making probabilistic decisions, mimicking the behavior of neurons in the brain. By harnessing the stochastic switching properties of PCMO RRAM, the system achieves remarkable efficiency in solving NP Hard problems.

Type of IP

Faculty

Category of Patent

Department

PrxCa1-xMnO3 based Stochastic Neuron for Boltzmann Machine to Solve “Maximum Cut" Problem
Societal Impact
  • Intuitive Decision-Making: Empowers everyday individuals with simplified tools for making informed decisions, enhancing problem-solving abilities. 
  • Improved Computing: Enhances everyday technology by contributing to the development of faster, more energy-efficient computing systems.
Salient technical features and Advantages of the Technology
  • Innovative Material Use: Employs PrxCa1-xMnO3 (PCMO) RRAM for stochastic neuron implementation. 
  • Analog Sigmoid Function: Utilizes PCMO's analog sigmoidal switching for probability-based spike generation. 
  • Integrated Synaptic and Neuronal Functionality: Combines analog synaptic and integrate-and-fire (IF) neuronal functions in PCMO RRAM. 
  • Intrinsic Stochasticity: Achieves stochastic behavior without external noise sources or magnetic fields. 
  • Superior Algorithm Performance: Outperforms heuristic algorithms like Goemans-Williamson in solving NP-hard problems.
  • Innovative Material Use: Employs PrxCa1-xMnO3 (PCMO) RRAM for stochastic neuron implementation. 
  • Analog Sigmoid Function: Utilizes PCMO's analog sigmoidal switching for probability-based spike generation. 
  • Integrated Synaptic and Neuronal Functionality: Combines analog synaptic and integrate-and-fire (IF) neuronal functions in PCMO RRAM. 
  • Intrinsic Stochasticity: Achieves stochastic behavior without external noise sources or magnetic fields. 
  • Superior Algorithm Performance: Outperforms heuristic algorithms like Goemans-Williamson in solving NP-hard problems.
Technology readiness level

3

Current Status of Technology
  • Experimental Validation: The stochastic switching behavior of PCMO RRAM has been experimentally demonstrated. 
  • Energy Efficiency: Current implementations show promising energy benchmarks compared to traditional von-Neumann architectures. 
  • Limited Scalability: Challenges remain in scaling the technology for large-scale integration in neuromorphic computing systems.
Relevant Industries

Semiconductor, Artificial Intelligence (AI), Neuromorphic computing, Information Technology (IT)

Applications or Domain
  • Enhancing artificial intelligence algorithms for improved pattern recognition and optimization tasks. 
  • Enabling energy-efficient and high-performance computing solutions for various industries such as healthcare, finance, and automotive.