Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/122315
Title: LEARNING DEEP REPRESENTATIONS: PLATFORM AND ALGORITHMS
Authors: LIN MIN
Keywords: Deep learning, Neural networks, Parallelization, Feedforward neural network, Convolutional neural network, Energy based model
Issue Date: 20-Aug-2015
Citation: LIN MIN (2015-08-20). LEARNING DEEP REPRESENTATIONS: PLATFORM AND ALGORITHMS. ScholarBank@NUS Repository.
Abstract: DEEP LEARNING HAS RECEIVED UNPRECEDENTED ATTENTION FROM RESEARCHERS OF DIFFERENT AREAS DURING THESE TWO YEARS. IN THIS THESIS, A SERIES OF WORKS ARE INTRODUCED WHICH CONTRIBUTE TO THE FIELD OF DEEP LEARNING IN TWO ASPECTS, NAMELY ?PLATFORM AND ALGORITHMS?. IN THE PLATFORM PART, A DEEP LEARNING PLATFORM CALLED PURINE IS DESIGNED BASED ON BI-GRAPH ABSTRACTION, PURINE ACCELERATE NEURAL NET TRAINING BY HARNESSING THE POWER OF MULTIPLE GPUS ON MULTIPLE MACHINES. IN THE ALGORITHMS PART, WE PROPOSED THE ?NETWORK IN NETWORK?(NIN) AND THE ?NEURAL DYNAMICAL SYSTEM?(NDS) ALGORITHMS. THE NIN ALGORITHM IS BUILT ON THE CONVOLUTIONAL NEURAL NETWORK STRUCTURE. IT ENHANCES THE LOCAL DISCRIMINATIVE POWER OF THE CONVOLUTIONAL NEURAL NETWORK BY REPLACING THE LINEAR CONVOLUTIONAL FILTERS WITH A FEEDFORWARD NEURAL NETWORK. THE NDS ALGORITHM ADDS FEEDBACK LOOPS TO THE FEEDFORWARD NEURAL NETS BASED ON A DIFFERENTIAL NEURON MODEL, WHICH GENERALIZES BOTH FEEDFORWARD NEURAL NETS AND ENERGY BASED MODELS.
URI: http://scholarbank.nus.edu.sg/handle/10635/122315
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LinM.pdf4.93 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

121
checked on Nov 9, 2018

Download(s)

48
checked on Nov 9, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.