US Patent Application 17804107. PARALLEL AND DISTRIBUTED PROCESSING OF PROPOSITIONAL LOGICAL NEURAL NETWORKS simplified abstract
Contents
PARALLEL AND DISTRIBUTED PROCESSING OF PROPOSITIONAL LOGICAL NEURAL NETWORKS
Organization Name
International Business Machines Corporation
Inventor(s)
Venkatesan Thirumalai Chakaravarthy of Karnataka (IN)
Anamitra Roy Choudhury of Vasant Kunj (IN)
Naweed Aghmad Khan of Johannesburg (ZA)
Francois Pierre Luus of Wierdapark (ZA)
Yogish Sabharwal of Gurgaon (IN)
PARALLEL AND DISTRIBUTED PROCESSING OF PROPOSITIONAL LOGICAL NEURAL NETWORKS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17804107 titled 'PARALLEL AND DISTRIBUTED PROCESSING OF PROPOSITIONAL LOGICAL NEURAL NETWORKS
Simplified Explanation
The patent application describes a system that uses a processor to identify weights in a propositional logical neural network and convert them into a sparse matrix. The system also converts a training set into bound vectors and updates the sparse matrix using a graphical processing unit (GPU). It computes a loss parameter and updates the weights of the neural network if the loss function is below a certain threshold.
- System identifies weights in a propositional logical neural network
- Weights are converted into a sparse matrix
- Training set is converted into bound vectors
- Sparse matrix is updated using a graphical processing unit (GPU)
- Loss parameter is computed
- Weights of the neural network are updated if loss function is below a threshold
Original Abstract Submitted
An embodiment may include a processor that identifies a plurality of weights from the propositional logical neural network. The embodiment may convert the plurality of weights into a sparse matrix. The embodiment may convert a training set into a plurality of bound vectors. The embodiment may update the sparse matrix using a graphical processing unit (GPU). The embodiment may compute a loss parameter and based on determining the loss function is below threshold, update the plurality of weights of the propositional neural network.
