IT1245954B - Metodo per accelerare la convergenza dell'algoritmo di back-propagation applicato per realizzare il processo di apprendimento in una rete neuronica del tipo perceptron multistrato - Google Patents

Metodo per accelerare la convergenza dell'algoritmo di back-propagation applicato per realizzare il processo di apprendimento in una rete neuronica del tipo perceptron multistrato

Info

Publication number
IT1245954B
IT1245954B ITRM910302A ITRM910302A IT1245954B IT 1245954 B IT1245954 B IT 1245954B IT RM910302 A ITRM910302 A IT RM910302A IT RM910302 A ITRM910302 A IT RM910302A IT 1245954 B IT1245954 B IT 1245954B
Authority
IT
Italy
Prior art keywords
network
samples
learning
convergence
propagation algorithm
Prior art date
Application number
ITRM910302A
Other languages
English (en)
Inventor
Girolamo Gallo
Original Assignee
Texas Instruments Italia Spa
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
Application filed by Texas Instruments Italia Spa filed Critical Texas Instruments Italia Spa
Priority to ITRM910302A priority Critical patent/IT1245954B/it
Publication of ITRM910302A0 publication Critical patent/ITRM910302A0/it
Priority to JP4114943A priority patent/JPH06161978A/ja
Publication of ITRM910302A1 publication Critical patent/ITRM910302A1/it
Application granted granted Critical
Publication of IT1245954B publication Critical patent/IT1245954B/it
Priority to US08/396,361 priority patent/US6016384A/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Character Discrimination (AREA)
  • Feedback Control In General (AREA)

Abstract

Oggetto dell'invenzione è un metodo per accelerare la convergenza dell'algoritmo di back-propagation applicato per realizzare il processo di apprendimento in una rete neuronica del tipo percepton multistrato destinata ad esempio al riconoscimento di un assieme di campioni, il quale metodo comprende una prima fase basata sul concetto di aumentare progressivamente la capacità di apprendimento della rete mediante aggiunta progressiva, ad un assieme iniziale di campioni di apprendimento, di nuovi campioni a mano a mano che essi vengono riconosciuti dalla rete; una seconda fase basata sul concetto di aumentare progressivamente la capacità di apprendimento della rete mediante aggiunta progressiva di campioni non precedentemente riconosciuti; ed una terza fase basata sul concetto di aumentare progressivamente la capacità di apprendimento della rete mediante corruzione progressiva in senso di assimilazione tra campioni riconosciuti e campioni non riconosciuti e loro successiva esposizione alla rete.
ITRM910302A 1991-05-07 1991-05-07 Metodo per accelerare la convergenza dell'algoritmo di back-propagation applicato per realizzare il processo di apprendimento in una rete neuronica del tipo perceptron multistrato IT1245954B (it)

Priority Applications (3)

Application Number Priority Date Filing Date Title
ITRM910302A IT1245954B (it) 1991-05-07 1991-05-07 Metodo per accelerare la convergenza dell'algoritmo di back-propagation applicato per realizzare il processo di apprendimento in una rete neuronica del tipo perceptron multistrato
JP4114943A JPH06161978A (ja) 1991-05-07 1992-05-07 多層パーセプトロン形神経状回路網における学習プロセスを実現するために適用されるバックプロパゲーション・アルゴリズムの収束の加速方法
US08/396,361 US6016384A (en) 1991-05-07 1995-02-28 Method for speeding up the convergence of the back-propagation algorithm applied to realize the learning process in a neural network of the multilayer perceptron type

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
ITRM910302A IT1245954B (it) 1991-05-07 1991-05-07 Metodo per accelerare la convergenza dell'algoritmo di back-propagation applicato per realizzare il processo di apprendimento in una rete neuronica del tipo perceptron multistrato

Publications (3)

Publication Number Publication Date
ITRM910302A0 ITRM910302A0 (it) 1991-05-07
ITRM910302A1 ITRM910302A1 (it) 1992-11-07
IT1245954B true IT1245954B (it) 1994-11-07

Family

ID=11400125

Family Applications (1)

Application Number Title Priority Date Filing Date
ITRM910302A IT1245954B (it) 1991-05-07 1991-05-07 Metodo per accelerare la convergenza dell'algoritmo di back-propagation applicato per realizzare il processo di apprendimento in una rete neuronica del tipo perceptron multistrato

Country Status (3)

Country Link
US (1) US6016384A (it)
JP (1) JPH06161978A (it)
IT (1) IT1245954B (it)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006098766A2 (en) * 2004-09-17 2006-09-21 Proximex Incremental data fusion and decision making system and associated method
US8266145B2 (en) * 2007-03-16 2012-09-11 1759304 Ontario Inc. Contextual data mapping, searching and retrieval
US20080275775A1 (en) * 2007-05-04 2008-11-06 Yahoo! Inc. System and method for using sampling for scheduling advertisements in an online auction
US9000918B1 (en) 2013-03-02 2015-04-07 Kontek Industries, Inc. Security barriers with automated reconnaissance
US9594983B2 (en) * 2013-08-02 2017-03-14 Digimarc Corporation Learning systems and methods
US11669746B2 (en) 2018-04-11 2023-06-06 Samsung Electronics Co., Ltd. System and method for active machine learning
WO2023132846A1 (en) * 2022-01-06 2023-07-13 Rowan University Training a neural network for a predictive aortic aneurysm detection system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1987006371A1 (en) * 1986-04-10 1987-10-22 Hewlett Packard Limited Expert system using pattern recognition techniques
US4805225A (en) * 1986-11-06 1989-02-14 The Research Foundation Of The State University Of New York Pattern recognition method and apparatus
US5052043A (en) * 1990-05-07 1991-09-24 Eastman Kodak Company Neural network with back propagation controlled through an output confidence measure
US5218529A (en) * 1990-07-30 1993-06-08 University Of Georgia Research Foundation, Inc. Neural network system and methods for analysis of organic materials and structures using spectral data

Also Published As

Publication number Publication date
ITRM910302A1 (it) 1992-11-07
JPH06161978A (ja) 1994-06-10
ITRM910302A0 (it) 1991-05-07
US6016384A (en) 2000-01-18

Similar Documents

Publication Publication Date Title
Callender Voice-leading parsimony in the music of Alexander Scriabin
IT1270919B (it) Sistema per il riconoscimento di parole isolate indipendente dal parlatore mediante reti neurali
IT1245954B (it) Metodo per accelerare la convergenza dell'algoritmo di back-propagation applicato per realizzare il processo di apprendimento in una rete neuronica del tipo perceptron multistrato
JPS6478299A (en) Voice recognition method and apparatus
Lohrenz et al. Multi-encoder learning and stream fusion for transformer-based end-to-end automatic speech recognition
WO2002015125A3 (en) Neural network device for evolving appropriate connections
KR920003189A (ko) 뉴-럴 네트워크 회로
Kohonen A self-learning musical grammar, or'Associative memory of the second kind'
Suh et al. Phoneme segmentation of continuous speech using multi-layer perceptron
IT1255446B (it) Apparato per il riconoscimento di accordi e relativo apparato di esecuzione automatica di accmpagnamenti musicali
Xing et al. On generating fuzzy systems based on pareto multi-objective cooperative coevolutionary algorithm
Cong et al. Silicon photonic hopfield-like electro-optical recurrent network for time-series data processing and recognition
Liang et al. A study of removing hidden neurons in cascade-correlation neural networks
Choi et al. Short-utterance embedding enhancement method based on time series forecasting technique for text-independent speaker verification
Zaborszky et al. On line stabilization of the large HV-AC-DC power system by using observation decoupled reference as a system-wide target
Irum et al. Fuzzy Logic Based Time Series Prediction Algorithm Using Nearest Neighborhood Clustering
SU1610541A1 (ru) Способ регулировани мощности емкостной компенсации
JP3318958B2 (ja) 学習型波形認識処理装置
Bodenhausen et al. Learning the architecture of neural networks for speech recognition.
Hwang et al. A dynamic approach to the Shapley value based on associated games
NO965051L (no) FremgangsmÕte ved seriedataoverf÷ring for gjenkjennelse av et fast m÷nster
He Dynamic Weight Adjustment in Siamese Multi-Head Self-Attention for Text Similarity
Tao et al. Speaker-independent speech recognition based on fast neural network
Wang et al. An adaptive and fully sparse training approach for multilayer perceptrons
Zhang et al. A new dynamic optimal learning rate for a two-layer neural network

Legal Events

Date Code Title Description
0001 Granted
TA Fee payment date (situation as of event date), data collected since 19931001

Effective date: 19960411