公开(公告)号：ZA202100291B

公开(公告)日：2022-02-23

申请号：ZA202100291

申请日：2021-01-15

Applicant: IBM

Inventor： AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED ,  LUUS FRANCOIS PIERRE ,  MAKONDO NDIVHUWO ,  RIEGEL RYAN ,  GRAY ALEXANDER

Abstract: Word sense disambiguation using a glossary layer embedded in a deep neural network includes receiving, by one or more processors, input sentences including a plurality of words. At least two words in the plurality of words are homonyms. The one or more processors convert the plurality of words associated with each input sentence into a first vector including possible senses for the at least two words. The first vector is then combined with a second vector including a domain-specific contextual vector associated with the at least two words. The combination of the first vector with the second vector is fed into a recurrent deep logico-neural network model to generate a third vector that includes word senses for the at least two words. A threshold is set for the third vector to generate a fourth vector including a final word sense vector for the at least two words.

公开(公告)号：ZA202100290B

公开(公告)日：2022-01-26

申请号：ZA202100290

申请日：2021-01-15

Applicant: IBM

Inventor： RIEGEL RYAN ,  LUUS FRANCOIS PIERRE ,  AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED ,  MAKONDO NDIVHUWO ,  BARAHONA FRANCISCO ,  GRAY ALEXANDER

Abstract: A system for configuring and using a logical neural network including a graph syntax tree of formulae in a represented knowledgebase connected to each other via nodes representing each proposition. One neuron exists for each logical connective occurring in each formula and, additionally, one neuron for each unique proposition occurring in any formula. All neurons return pairs of values representing upper and lower bounds on truth values of their corresponding subformulae and propositions. Neurons corresponding to logical connectives accept as input the output of neurons corresponding to their operands and have activation functions configured to match the connectives' truth functions. Neurons corresponding to propositions accept as input the output of neurons established as proofs of bounds on the propositions' truth values and have activation functions configured to aggregate the tightest such bounds. Bidirectional inference permits every occurrence of each proposition in each formula to be used as a potential proof.

公开(公告)号：ZA201904992B

公开(公告)日：2020-05-27

申请号：ZA201904992

申请日：2019-07-30

Applicant: IBM

Inventor： KURIEN TOBY ,  GRITZMAN ASHLEY D ,  AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED

Abstract: A method 30 and system 10 for facilitating safe handling of a physical medium of financial exchange, such as cash notes is provided to prevent cash-in-transit heists. The method 30 includes physically marking 33, using a first processing device 8, cash with a unique owner identifier which is associated with the owner of the cash, and physically invalidating 34 the cash through cutting, staining or stamping it. Once invalidated, the worthless cash can be transported risk-free to a desired cash processing facility. Upon arrival, the method includes verifying 44, using an authentication module 24, authenticity of the unique owner identifier and cash notes themselves. If verification fails, law enforcement is notified. If passed, the cash is destroyed 38, using a second processing device 9 which digitizes, using a digitizer 22, the cash notes and transfers a digital equivalent value, which is credited to the owner's account, to an electronic record keeping system 12.