公开(公告)号：AU2021269906A1

公开(公告)日：2022-10-27

申请号：AU2021269906

申请日：2021-04-13

Applicant: IBM

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

IPC: G06N3/04

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：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：AU2021271230A1

公开(公告)日：2022-10-27

申请号：AU2021271230

申请日：2021-03-18

Applicant: IBM

Inventor： LUUS FRANCOIS ,  RIEGEL RYAN ,  AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED AGHMAD ,  VOS ETIENNE ,  MAKONDO NDIVHUWO

IPC: G06N3/04

Abstract: Maximum expressivity can be received representing a ratio between maximum and minimum input weights to a neuron of a neural network implementing a weighted real-valued logic gate. Operator arity can be received associated with the neuron. Logical constraints associated with the weighted real-valued logic gate can be determined in terms of weights associated with inputs to the neuron, a threshold-of-truth, and a neuron threshold for activation. The threshold-of-truth can be determined as a parameter used in an activation function of the neuron, based on solving an activation optimization formulated based on the logical constraints, the activation optimization maximizing a product of expressivity representing a distribution width of input weights to the neuron and gradient quality for the neuron given the operator arity and the maximum expressivity. The neural network of logical neurons can be trained using the activation function at the neuron, the activation function using the determined threshold-of-truth.

公开(公告)号：ZA202103206B

公开(公告)日：2022-08-31

申请号：ZA202103206

申请日：2021-05-12

Applicant: IBM

Inventor： LUUS FRANCOIS PIERRE ,  RIEGEL RYAN ,  AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED AGHMAD ,  VOS ETIENNE EBEN ,  MAKONDO NDIVHUWO

Abstract: Maximum expressivity can be received representing a ratio between maximum and minimum input weights to a neuron of a neural network implementing a weighted real-valued logic gate. Operator arity can be received associated with the neuron. Logical constraints associated with the weighted real-valued logic gate can be determined in terms of weights associated with inputs to the neuron, a threshold-of-truth, and a neuron threshold for activation. The threshold-of-truth can be determined as a parameter used in an activation function of the neuron, based on solving an activation optimization formulated based on the logical constraints, the activation optimization maximizing a product of expressivity representing a distribution width of input weights to the neuron and gradient quality for the neuron given the operator arity and the maximum expressivity. The neural network of logical neurons can be trained using the activation function at the neuron, the activation function using the determined threshold-of-truth.