INSTRUCTION TO QUERY FOR MODEL-DEPENDENT INFORMATION

Patent №

US 11,675,592

Granted

2023-06-13

Filed 2021

Owner

INTERNATIONAL BUSINESS MACHINES CORPORATION

Lab

IBM Research

AI components

kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

17350326

An instruction is executed to perform a query function. The executing includes obtaining information relating to a selected model of a processor. The information includes at least one model-dependent data attribute of the selected model of the processor. The information is placed in a selected location for use by at least one application in performing one or more functions.

Knowledge representation AI hardwareG06F 9/383G06F 9/30036G06F 9/30076G06F 11/0772G06N 3/048G06N 3/063

Google Patents

AI classification

AI hardware1.00

Knowledge representation0.83

Planning0.15

Natural language0.15

Speech0.05

Machine learning0.00

Evolutionary computation0.00

Vision0.00

Ownership

INTERNATIONAL BUSINESS MACHINES CORPORATION

assignment · 565790028

Assignors

SLEGEL, TIMOTHY, ALBARAKAT, LAITH M., BRADBURY, JONATHAN D., LICHTENAU, CEDRIC, WEISHAUPT, SIMON

On an employer assignment, the assignors are typically the inventors.

From the same owner

METRIC LEARNING PREDICTION OF SIMULATION PARAMETERSUS 12,691,869 · 2026 DETERMINATION AND ALLEVIATION OF ROOT CAUSES FOR EMISSION OF POLLUTANTS FROM VEHICLESUS 12,693,686 · 2026 TRAINING AND USING A SENTIMENT MACHINE LEARNING MODULE TO RECEIVE AS INPUT HAPTIC METRIC VALUES TO DETERMINE A SENTIMENT SCORE FOR TEXT TO PROVIDE TO AN INTERACTIVE PROGRAMUS 12,693,779 · 2026 DOMAIN-SPECIFICITY PREDICTION FOR NATURAL LANGUAGE PROCESSINGUS 12,694,208 · 2026 USER INTERFACE AUTOMATION USING NATURAL LANGUAGEUS 12,694,222 · 2026 NATURAL LANGUAGE DATA GENERATION USING AUTOMATED KNOWLEDGE DISTILLATION TECHNIQUESUS 12,694,236 · 2026 NEURAL NETWORK SYSTEMS FOR ABSTRACT REASONINGUS 12,694,281 · 2026 ACCELERATING INFERENCE OF NEURAL NETWORK MODELS VIA DYNAMIC EARLY EXITSUS 12,694,283 · 2026

Cites (31)

SPARSE CONVOLUTIONAL NEURAL NETWORK ACCELERATORUS 10,891,538 · 2021 On-Device Neural Networks for Natural Language UnderstandingUS 10,885,277 · 2021 MERGING MULTIPLE NODAL NETWORKSUS 10,832,137 · 2020 NEURAL NETWORK ACCELERATION AND EMBEDDING COMPRESSION SYSTEMS AND METHODS WITH ACTIVATION SPARSIFICATIONUS 10,832,139 · 2020 DEVICE FOR IMPLEMENTING ARTIFICIAL NEURAL NETWORK WITH FLEXIBLE BUFFER POOL STRUCTUREUS 10,824,939 · 2020 POWER SAVINGS FOR NEURAL NETWORK ARCHITECTURE WITH ZERO ACTIVATIONS DURING INFERENCEUS 10,817,042 · 2020 HARDWARE ACCELERATOR FOR COMPRESSED GRU ON FPGAUS 10,810,484 · 2020 COMBINING CPU AND SPECIAL ACCELERATOR FOR IMPLEMENTING AN ARTIFICIAL NEURAL NETWORKUS 10,802,992 · 2020 COMPILER AND HARDWARE ABSTRACTION LAYER ARCHITECTURE FOR A NEURAL NETWORK ACCELERATORUS 10,789,402 · 2020 OUTLIER DETECTION FOR STREAMING DATA USING LOCALITY SENSITIVE HASHINGUS 10,778,707 · 2020 METHOD AND APPARATUS FOR DESIGNING AND IMPLEMENTING A CONVOLUTION NEURAL NET ACCELERATORUS 10,726,328 · 2020 DATA STRUCTURE DESCRIPTORS FOR DEEP LEARNING ACCELERATIONUS 10,726,329 · 2020 INSTANCE UPGRADE MIGRATIONUS 10,728,169 · 2020 CLUSTER OF SCALAR ENGINES TO ACCELERATE INTERSECTION IN LEAF NODEUS 10,699,465 · 2020 ENHANCED LOW PRECISION BINARY FLOATING-POINT FORMATTINGUS 10,656,913 · 2020 SYSTEM AND METHOD FOR INCREASING ACCURACY OF APPROXIMATING QUERY RESULTS USING NEURAL NETWORKSUS 10,642,835 · 2020 MATRIX MULTIPLICATION ACCELERATION OF SPARSE MATRICES USING COLUMN FOLDING AND SQUEEZINGUS 10,620,951 · 2020 METHOD AND APPARATUS FOR LOADING A MATRIX INTO AN ACCELERATORUS 10,558,599 · 2020 SYSTEM AND METHOD FOR BINARY THROTTLING FOR LIVE MIGRATION OF VIRTUAL MACHINESUS 10,552,199 · 2020 REDUCING COMPUTATIONS IN A NEURAL NETWORKUS 10,460,230 · 2019 NEURAL NETWORK UNIT WITH SHARED ACTIVATION FUNCTION UNITSUS 10,387,366 · 2019 TININESS PREDICTION AND HANDLER ENGINE FOR SMOOTH HANDLING OF NUMERIC UNDERFLOWUS 10,379,814 · 2019 Tensor Register FilesUS 10,338,925 · 2019 MACHINE LEARNING MODEL REPOSITORYUS 10,275,710 · 2019 DATA SUMMARY VIEW WITH FILTERINGUS 10,204,093 · 2019

and 6 more

Related research

INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval ModelsarXiv Demonstration of Accelerating Machine Learning Inference Queries with Correlative Proxy ModelsSemantic Scholar A Study on Instruction Formats on Computer Organization and ArchitectureOpenAlex Models are Data Too: Towards Expressive Querying of Machine-learning ModelsOpenAlex Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code GenerationarXiv

Full text

Google Patents