WO2017165904A3 - Method for operating a digital computer to reduce the computational complexity associated with dot products between large vectors - Google Patents

Method for operating a digital computer to reduce the computational complexity associated with dot products between large vectors Download PDF

Info

Publication number
WO2017165904A3
WO2017165904A3 PCT/AU2017/000071 AU2017000071W WO2017165904A3 WO 2017165904 A3 WO2017165904 A3 WO 2017165904A3 AU 2017000071 W AU2017000071 W AU 2017000071W WO 2017165904 A3 WO2017165904 A3 WO 2017165904A3
Authority
WO
WIPO (PCT)
Prior art keywords
vector
operating
vectors
reduce
digital computer
Prior art date
Application number
PCT/AU2017/000071
Other languages
French (fr)
Other versions
WO2017165904A2 (en
Inventor
Vincenzo Liguori
Original Assignee
Ocean Logic Pty Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from AU2016901146A external-priority patent/AU2016901146A0/en
Application filed by Ocean Logic Pty Ltd filed Critical Ocean Logic Pty Ltd
Priority to KR1020187030590A priority Critical patent/KR20180122021A/en
Priority to CN201780022940.2A priority patent/CN109074350A/en
Publication of WO2017165904A2 publication Critical patent/WO2017165904A2/en
Publication of WO2017165904A3 publication Critical patent/WO2017165904A3/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06G—ANALOGUE COMPUTERS
    • G06G7/00—Devices in which the computing operation is performed by varying electric or magnetic quantities
    • G06G7/12—Arrangements for performing computing operations, e.g. operational amplifiers
    • G06G7/22—Arrangements for performing computing operations, e.g. operational amplifiers for evaluating trigonometric functions; for conversion of co-ordinates; for computations involving vector quantities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06G—ANALOGUE COMPUTERS
    • G06G7/00—Devices in which the computing operation is performed by varying electric or magnetic quantities
    • G06G7/12—Arrangements for performing computing operations, e.g. operational amplifiers
    • G06G7/16—Arrangements for performing computing operations, e.g. operational amplifiers for multiplication or division
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06G—ANALOGUE COMPUTERS
    • G06G7/00—Devices in which the computing operation is performed by varying electric or magnetic quantities
    • G06G7/12—Arrangements for performing computing operations, e.g. operational amplifiers
    • G06G7/26—Arbitrary function generators
    • G06G7/28—Arbitrary function generators for synthesising functions by piecewise approximation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computational Mathematics (AREA)
  • Algebra (AREA)
  • Computer Hardware Design (AREA)
  • Neurology (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Complex Calculations (AREA)
  • Power Engineering (AREA)
  • Image Processing (AREA)

Abstract

The present invention includes a method for operating a data processing system to compute an approximation to a scalar product between first and second vectors in which each vector is characterized by N components. The method includes replacing the first vector by a third vector that is a pyramid integer vector characterized by N components and an integer K equal to the sum of the absolute values of the N components, and computing a scalar product of the third vector with the second vector to provide the approximation to the scalar product between the first and second vectors. Computing the scalar product of the second and third vectors can be carried out by K additions followed by one floating point multiply.
PCT/AU2017/000071 2016-03-29 2017-03-23 Method for operating a digital computer to reduce the computational complexity associated with dot products between large vectors WO2017165904A2 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1020187030590A KR20180122021A (en) 2016-03-29 2017-03-23 How to operate a digital computer to reduce computational complexity associated with dot products between large vectors
CN201780022940.2A CN109074350A (en) 2016-03-29 2017-03-23 Method for operating digital computer to reduce the associated computation complexity of the dot product between big vector

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
AU2016901146A AU2016901146A0 (en) 2016-03-29 Vector Quantization for Machine Vision
AU2016901146 2016-03-29

Publications (2)

Publication Number Publication Date
WO2017165904A2 WO2017165904A2 (en) 2017-10-05
WO2017165904A3 true WO2017165904A3 (en) 2018-08-23

Family

ID=59962302

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/AU2017/000071 WO2017165904A2 (en) 2016-03-29 2017-03-23 Method for operating a digital computer to reduce the computational complexity associated with dot products between large vectors

Country Status (3)

Country Link
KR (1) KR20180122021A (en)
CN (1) CN109074350A (en)
WO (1) WO2017165904A2 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130246496A1 (en) * 2010-09-24 2013-09-19 Arm Limited Floating-point vector normalisation
US20140126824A1 (en) * 2012-11-05 2014-05-08 Raytheon Bbn Technologies Corp. Efficient inner product computation for image and video analysis
US20140172937A1 (en) * 2012-12-19 2014-06-19 United States Of America As Represented By The Secretary Of The Air Force Apparatus for performing matrix vector multiplication approximation using crossbar arrays of resistive memory devices

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130246496A1 (en) * 2010-09-24 2013-09-19 Arm Limited Floating-point vector normalisation
US20140126824A1 (en) * 2012-11-05 2014-05-08 Raytheon Bbn Technologies Corp. Efficient inner product computation for image and video analysis
US20140172937A1 (en) * 2012-12-19 2014-06-19 United States Of America As Represented By The Secretary Of The Air Force Apparatus for performing matrix vector multiplication approximation using crossbar arrays of resistive memory devices

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ANDY C. HUNG ET AL.: "Error-Resilient Pyramid Vector Quantization for Image Compression", IN: IEEE TRANSACTIONS ON IMAGE PROCESSING, vol. 7, no. 10, October 1998 (1998-10-01), pages 1373 - 1386, XP000782308 *
MER EGECIOGLU ET AL.: "Dimensionality Reduction and Similarity Computation by Inner-Product Approximations", IN: IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, vol. 16, no. 6, June 2004 (2004-06-01), pages 714 - 726, XP058105605 *

Also Published As

Publication number Publication date
KR20180122021A (en) 2018-11-09
CN109074350A (en) 2018-12-21
WO2017165904A2 (en) 2017-10-05

Similar Documents

Publication Publication Date Title
WO2019046317A8 (en) Key data processing method and apparatus, and server
MX2017009879A (en) Batch normalization layers.
MX2023010407A (en) Accelerated mathematical engine.
CA3083043A1 (en) System and method of floating point multiply operation processing
MX2019011211A (en) Transform method in image coding system and apparatus for same.
EP3664705A4 (en) Systems, devices, and methods for image processing to generate an image having predictive tagging
PH12019500288A1 (en) Video encoding and decoding
EP3624020A4 (en) Computing method and related product
GB2545607A (en) Apparatus and method for vector processing with selective rounding mode
MY183126A (en) Video picture coding method, video picture decoding method, coding device, and decoding device
GB2567372A (en) Outer product engine
GB201309683D0 (en) Graphics processing
WO2018052606A3 (en) Apparatus and method for optimized ray tracing
WO2017032459A8 (en) System and method of digital note taking
EP3651018A3 (en) Systems and methods for performing 16-bit floating-point vector dot product instructions
MX2019004025A (en) Systems and methods for synchronizing database schema.
EP3818439A4 (en) Systems and methods for implementing an intelligence processing computing architecture
WO2015199779A3 (en) Flexible vector-processing algorithms for numerically solving extreme-scale, linear and non-linear, predictive and prescriptive, problems in science and engineering, on parallel-processing super computers
EP3728998A4 (en) Method, system, and computer program product for wait time estimation using predictive modeling
WO2020016482A3 (en) Computation of user-specific item-related values on an electronic processing platform
Ma et al. Automorphisms of the zero-divisor graph over $2\\times 2$ matrices
MX2018004316A (en) Reception apparatus, transmission apparatus, and data processing method.
TW201612850A (en) Image processing system and saturation compensation method
MX2017002329A (en) Systems and methods for recipient-side image processing.
WO2017165904A3 (en) Method for operating a digital computer to reduce the computational complexity associated with dot products between large vectors

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20187030590

Country of ref document: KR

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17772862

Country of ref document: EP

Kind code of ref document: A2

122 Ep: pct application non-entry in european phase

Ref document number: 17772862

Country of ref document: EP

Kind code of ref document: A2