Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019067542) JOINT OPTIMIZATION OF ENSEMBLES IN DEEP LEARNING
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2019/067542 International Application No.: PCT/US2018/052857
Publication Date: 04.04.2019 International Filing Date: 26.09.2018
IPC:
G06N 5/02 (2006.01) ,G06N 5/04 (2006.01) ,G06F 17/30 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5
Computer systems utilizing knowledge based models
02
Knowledge representation
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5
Computer systems utilizing knowledge based models
04
Inference methods or devices
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
F
ELECTRIC DIGITAL DATA PROCESSING
17
Digital computing or data processing equipment or methods, specially adapted for specific functions
30
Information retrieval; Database structures therefor
Applicants:
D5AI LLC [US/US]; 958 Versailles Cirlcle Maitland, FL 32751, US
Inventors:
BAKER, James, K.; US
Agent:
KNEDEISEN, Mark, G.; US
CONRAD, Sean, M.; US
CAPRIOTTI, Roberto; US
BLYTH, Gareth, M.; US
ANDERSON, Jaimie, R.; US
Priority Data:
62/564,75428.09.2017US
62/696,06310.07.2018US
Title (EN) JOINT OPTIMIZATION OF ENSEMBLES IN DEEP LEARNING
(FR) OPTIMISATION CONJOINTE D'ENSEMBLES EN APPRENTISSAGE PROFOND
Abstract:
(EN) Computer-implemented, machine-learning systems and methods relate to a combination of neural networks. The systems and methods train the respective member networks both (i) to be diverse and yet (ii) according to a common, overall objective. Each member network is trained or retrained jointly with all the other member networks, including member networks that may not have been present in the ensemble when a member is first trained.
(FR) L'invention concerne des systèmes et des procédés d'apprentissage automatique mis en œuvre par ordinateur qui concernent une combinaison de réseaux neuronaux. Les systèmes et les procédés entraînent les réseaux membres respectifs à la fois (i) pour être différents et néanmoins (ii) selon un objectif global commun. Chaque réseau membre est entraîné ou ré-entraîné conjointement avec tous les autres réseaux membres, y compris des réseaux membres qui peuvent ne pas avoir été présents dans l'ensemble lorsqu'un membre a été entraîné pour la première fois.
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)