Deep learning in kernel methods (Record no. 6629)

MARC details
000 -LEADER
fixed length control field 03141nam a22001937a 4500
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20220107122855.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 191023b xxu||||| |||| 00| 0 eng d
040 ## - CATALOGING SOURCE
Transcribing agency IIITMK
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Afzal A L
9 (RLIN) 16890
245 ## - TITLE STATEMENT
Title Deep learning in kernel methods
Statement of responsibility, etc. Afzal A L
300 ## - PHYSICAL DESCRIPTION
Extent PHD Thesis 2018
500 ## - GENERAL NOTE
General note The attempt to build algorithms to solve cognitive tasks such as visual object or <br/>pattern recognition, speech perception, language understanding etc. have attracted the<br/>attention of many machine learning researchers in the recent past. The theoretical and<br/>biological arguments in this context strongly suggest that building such systems requires<br/>deep learning architectures that involve many layers of nonlinear information processing. <br/>Deep learning approach has originally emerged and been widely used in the area<br/>of neural networks. The techniques developed from deep learning research have already<br/>been impacting a wide range of signal and information processing applications. In the<br/>recent past, excited by the startling performance that deep learning approaches have to<br/>offer, there are many attempts to embrace deep learning techniques in other machine<br/>learning paradigms, particularly in kernel machines. Convex optimization, structural<br/>risk minimization, margin maximization, etc. are the some of the elegant features that<br/>makes kernel machines popular among the researchers. With the advent of recently<br/>developed multi layered kernel called arc-cosine kernel, the multilayer computations is<br/>made possible in kernel machines. The multi-layered feature learning perceptiveness of<br/>deep learning architecture have been re-created in kernel machines through the model<br/>called Multilayer Kernel Machines(MKMs). Support vector machines were often used<br/>as the classifier in these models. These deep models have been widely used in many<br/>applications that involves small-size datasets. However the scalability, <br/>multilayer multiple kernel learning, unsupervised feature learning etc. were untouched in the context<br/>of kernel machines. This research explored above problems and developed three deep<br/>kernel learning models viz; (i) Deep kernel learning in core vector machine that analyze the <br/>behavior of arc-cosine kernel and modeled a scalable deep kernel machine by<br/>incorporating arc-cosine kernel in core vector machines. (ii) Deep multiple multilayer<br/>kernel learning in core vector machines modeled a scalable deep learning architecture<br/>with unsupervised feature extraction. Each feature extraction layer in this model exploit<br/>multiple kernel learning framework that involves both single layer and multilayer kernel<br/>computations. (iii) Deep kernel based extreme learning machine combines the multilayer <br/>kernel computation of arc-cosine kernel and fast, non-iterative learning mechanism<br/>of Extreme Learning Machines. The theoretical and empirical analysis of the proposed<br/>methods show promising results.<br/>
502 ## - DISSERTATION NOTE
Degree type PhD Thesis
Name of granting institution September 2018
Year degree granted INT
-- Dr Asharaf S<br/>IIITMK
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element DEEP LEARNING
9 (RLIN) 16891
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element KERNEL MACHINES
9 (RLIN) 16892
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element MULTILAYER KERNEL MACHINES
9 (RLIN) 16893
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Collection code Home library Current library Shelving location Date acquired Total Checkouts Barcode Date last seen Price effective from Koha item type
    Dewey Decimal Classification     Non Fiction IIITM-K IIITM-K   23/10/2019   TH-7 23/10/2019 23/10/2019 Thesis