WO2020095321A3 - Dynamic structure neural machine for solving prediction problems with uses in machine learning - Google Patents

Dynamic structure neural machine for solving prediction problems with uses in machine learning Download PDF

Info

Publication number
WO2020095321A3
WO2020095321A3 PCT/IN2019/050820 IN2019050820W WO2020095321A3 WO 2020095321 A3 WO2020095321 A3 WO 2020095321A3 IN 2019050820 W IN2019050820 W IN 2019050820W WO 2020095321 A3 WO2020095321 A3 WO 2020095321A3
Authority
WO
WIPO (PCT)
Prior art keywords
dynamic structure
dsnn
dsnl
structure neural
novel
Prior art date
Application number
PCT/IN2019/050820
Other languages
French (fr)
Other versions
WO2020095321A2 (en
WO2020095321A8 (en
Inventor
Vishwajeet Singh Thakur
Original Assignee
Vishwajeet Singh Thakur
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 Vishwajeet Singh Thakur filed Critical Vishwajeet Singh Thakur
Publication of WO2020095321A2 publication Critical patent/WO2020095321A2/en
Publication of WO2020095321A3 publication Critical patent/WO2020095321A3/en
Publication of WO2020095321A8 publication Critical patent/WO2020095321A8/en

Links

Classifications

    • 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
    • G06N3/08—Learning methods
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology

Abstract

This invention discloses a new and novel methodology which can be used to solve multiclass classification problems in an automated way. It describes a novel neural network architecture "Dynamic Structure Neural Network (DSNN)", a novel automated learning method "Dynamic Structure Neural Learning (DSNL)" for training DSNN models and a product "Dynamic Structure Neural Machine (DSNM)" which is a computer-implementation of DSNN and DSNL for solving multiclass classification problems, such as, Medical Diagnosis, Face Recognition, Sentiment Analysis, Speech Recognition e.t.c. The system and method given in this invention analyzes any (structured, semi-structured or unstructured) type and form of data that can be vectorized. The novelty of this method is the architecture of the DSNN model and automated learning method DSNL that simultaneously determines the number of hidden layers, number of processing units (or neurons) in each hidden layer hidden layer and their parameters (weight and biases).
PCT/IN2019/050820 2018-11-06 2019-11-05 Dynamic structure neural machine for solving prediction problems with uses in machine learning WO2020095321A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IN201841041940 2018-11-06
IN201841041940 2018-11-06

Publications (3)

Publication Number Publication Date
WO2020095321A2 WO2020095321A2 (en) 2020-05-14
WO2020095321A3 true WO2020095321A3 (en) 2020-06-25
WO2020095321A8 WO2020095321A8 (en) 2020-07-23

Family

ID=70611488

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IN2019/050820 WO2020095321A2 (en) 2018-11-06 2019-11-05 Dynamic structure neural machine for solving prediction problems with uses in machine learning

Country Status (1)

Country Link
WO (1) WO2020095321A2 (en)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112085157B (en) * 2020-07-20 2024-02-27 西安电子科技大学 Disease prediction method and device based on neural network and tree model
CN112116143B (en) * 2020-09-14 2023-06-13 贵州大学 Forest pest occurrence probability calculation processing method based on neural network
CN113282842A (en) * 2021-01-25 2021-08-20 上海海事大学 Travel purpose identification method based on travel survey of smart phone and artificial neural network particle swarm optimization algorithm
CN112697435B (en) * 2021-01-26 2022-09-09 山西三友和智慧信息技术股份有限公司 Rolling bearing fault diagnosis method based on improved SELD-TCN network
CN112908446B (en) * 2021-03-20 2022-03-22 张磊 Automatic mixing control method for liquid medicine in endocrinology department
CN113469339B (en) * 2021-06-30 2023-09-22 山东大学 Automatic driving neural network robustness verification method and system based on dimension reduction
CN113590748B (en) * 2021-07-27 2024-03-26 中国科学院深圳先进技术研究院 Emotion classification continuous learning method based on iterative network combination and storage medium
CN114239330B (en) * 2021-11-01 2022-06-10 河海大学 Deep learning-based large-span latticed shell structure form creation method
CN115534319B (en) * 2022-09-21 2023-08-11 成都航空职业技术学院 3D printing path planning method based on HGEFS algorithm
CN115394394B (en) * 2022-10-27 2023-04-07 曹县人民医院 Resident health service reservation method and system based on big data processing technology
CN117537951B (en) * 2024-01-10 2024-03-26 西南交通大学 Method and device for detecting internal temperature rise of superconducting suspension based on deep learning

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7711663B2 (en) * 2006-03-27 2010-05-04 Board Of Trustees Of Michigan State University Multi-layer development network having in-place learning
US20180284737A1 (en) * 2016-05-09 2018-10-04 StrongForce IoT Portfolio 2016, LLC Methods and systems for detection in an industrial internet of things data collection environment with large data sets
US10095718B2 (en) * 2013-10-16 2018-10-09 University Of Tennessee Research Foundation Method and apparatus for constructing a dynamic adaptive neural network array (DANNA)

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7711663B2 (en) * 2006-03-27 2010-05-04 Board Of Trustees Of Michigan State University Multi-layer development network having in-place learning
US10095718B2 (en) * 2013-10-16 2018-10-09 University Of Tennessee Research Foundation Method and apparatus for constructing a dynamic adaptive neural network array (DANNA)
US20180284737A1 (en) * 2016-05-09 2018-10-04 StrongForce IoT Portfolio 2016, LLC Methods and systems for detection in an industrial internet of things data collection environment with large data sets

Also Published As

Publication number Publication date
WO2020095321A2 (en) 2020-05-14
WO2020095321A8 (en) 2020-07-23

Similar Documents

Publication Publication Date Title
WO2020095321A8 (en) Dynamic structure neural machine for solving prediction problems with uses in machine learning
Khalil et al. Energy efficiency prediction using artificial neural network
Zhang et al. A digital liquid state machine with biologically inspired learning and its application to speech recognition
Wysoski et al. Evolving spiking neural networks for audiovisual information processing
Kazerounian et al. Real-time learning of predictive recognition categories that chunk sequences of items stored in working memory
Milde et al. Using representation learning and out-of-domain data for a paralinguistic speech task.
Martinez-Maldonado et al. An automatic approach for mining patterns of collaboration around an interactive tabletop
Asogwa et al. Of students academic performance rates using artificial neural networks (ANNs)
Mansouri-Benssassi et al. Speech emotion recognition with early visual cross-modal enhancement using spiking neural networks
Siddique et al. Zara returns: Improved personality induction and adaptation by an empathetic virtual agent
Chawan et al. Distracted driver detection and classification
Hasan et al. Analysing hate speech against migrants and women through tweets using ensembled deep learning model
US11727338B2 (en) Controlling submission of content
Esposito et al. On the recognition of emotional vocal expressions: motivations for a holistic approach
Wu et al. Information-dense actions as contexts
Dasgupta et al. Voiceprint analysis for Parkinson's disease using MFCC, GMM, and instance based learning and multilayer perceptron
Balas et al. Low-level orientation information for social evaluation in face images
Prickett Vanilla sequence-to-sequence neural nets cannot model reduplication
Sagala Algorithm Modified K-Nearest Neighbor (M-KNN) for Classification of Attention Deficit Hyperactive Disorder (ADHD) in Children
Setiawan et al. The Effect of World Happiness Aspects with COVID-19 Infected using Machine Learning Multiple Regression Model
Plebe et al. A biologically inspired neural model of vision-language integration
Demircan et al. Language aligned visual representations predict human behavior in naturalistic learning tasks
Delbruck et al. Research topic: neuromorphic engineering systems and applications. A snapshot of neuromorphic systems engineering
Kasabov et al. Audio-and Visual Information Processing in the Brain and Its Modelling with Evolving SNN
Mayer et al. Wug-testing Uyghur vowel harmony

Legal Events

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

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19882268

Country of ref document: EP

Kind code of ref document: A2

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

Ref document number: 19882268

Country of ref document: EP

Kind code of ref document: A2

122 Ep: pct application non-entry in european phase

Ref document number: 19882268

Country of ref document: EP

Kind code of ref document: A2