Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019009897) SYSTEMS AND METHODS FOR COMPRESSION AND DISTRIBUTION OF MACHINE LEARNING MODELS
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2019/009897 International Application No.: PCT/US2017/040798
Publication Date: 10.01.2019 International Filing Date: 06.07.2017
Chapter 2 Demand Filed: 14.06.2018
IPC:
G06N 3/063 (2006.01) ,G06F 7/483 (2006.01) ,G06N 3/04 (2006.01) ,G06N 3/08 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
06
Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063
using electronic means
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
F
ELECTRIC DIGITAL DATA PROCESSING
7
Methods or arrangements for processing data by operating upon the order or content of the data handled
38
Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
48
using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
483
Computations with numbers represented by a non-linear combination of denominational numbers, e.g. rational numbers, logarithmic number system or floating-point numbers
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
04
Architecture, e.g. interconnection topology
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
08
Learning methods
Applicants:
GOOGLE LLC [US/US]; 1600 Amphitheatre Parkway Mountain View, California 94043, US
Inventors:
ALAKUIJALA, Jyrki; US
OBRYK, Robert; US
Agent:
MCKAY, Douglas E.; US
BATAVIA, Neil, M.; US
KENNEDY, Richard; 200 Aldersgate London EC1A 4HD, GB
Priority Data:
Title (EN) SYSTEMS AND METHODS FOR COMPRESSION AND DISTRIBUTION OF MACHINE LEARNING MODELS
(FR) SYSTÈMES ET PROCÉDÉS DE COMPRESSION ET DE DISTRIBUTION DE MODÈLES D'APPRENTISSAGE-MACHINE
Abstract:
(EN) The present disclosure provides systems and methods for compressing and/or distributing machine learning models. In one example, a computer-implemented method is provided to compress machine-learned models, which includes obtaining, by one or more computing devices, a machine-learned model. The method includes selecting, by the one or more computing devices, a weight to be quantized and quantizing, by the one or more computing devices, the weight. The method includes propagating, by the one or more computing devices, at least a part of a quantization error to one or more non-quantized weights and quantizing, by the one or more computing devices, one or more of the non-quantized weights. The method includes providing, by the one or more computing devices, a quantized machine-learned model.
(FR) La présente invention concerne des systèmes et des procédés de compression et/ou distribution de modèles d'apprentissage-machine. Dans un exemple, un procédé mis en œuvre par ordinateur est prévu pour compresser des modèles appris par machine, ce qui consiste à obtenir, par un ou plusieurs dispositif(s) informatique(s), un modèle appris par machine. Le procédé consiste à sélectionner, par le ou les dispositif(s) informatique(s), un poids à quantifier et à quantifier, par le ou les dispositif(s) informatique(s), ledit poids. Le procédé consiste à propager, par le ou les dispositif(s) informatique(s), au moins une partie d'une erreur de quantification vers un ou plusieurs poids non quantifiés et à quantifier, par le ou les dispositif(s) informatique(s), un ou plusieurs des poids non quantifiés. Le procédé consiste à fournir, par le ou les dispositif(s) informatique(s), un modèle quantifié appris par machine.
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JO, JP, KE, KG, KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (EPO) (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: English (EN)
Filing Language: English (EN)