Search
Now showing items 1-7 of 7
SECOND ORDER ALGORITHM FOR SPARSELY CONNECTED NEURAL NETWORKS
(2016-08-17)
A systematic two-step batch approach for constructing a sparse neural network is presented. Unlike other sparse neural networks, the proposed paradigm uses orthogonal least squares (OLS) to train the network. OLS based ...
MULTILAYER PERCEPTRON WITH ADAPTIVE ACTIVATION FUNCTIONS
(2016-05-26)
A Multilayer perceptron typically has a fixed nonlinear activation function for each hidden unit. In this thesis, an adaptive activation function for individual hidden unit is designed, where the network learns these ...
MACHINE LEARNING FOR TARGET DETECTION USING UWB RADAR SENSOR NETWORKS
(2022-12-05)
Machine learning (ML) has recently been used to solve critical problems. This dissertation focuses on developing systems using Ultra-Wideband (UWB) wireless sensor networks and machine learning to solve critical tasks such ...
UNSUPERVISED DATA DRIVEN MACHINE LEARNING IN HYPERSPECTRAL IMAGING AND ECHOCARDIOGRAPHY VIDEOS
(2021-05-06)
This work discusses the problem of unsupervised classification in images. Conventional methods approached this problem with the naive assumption that the relationship among the pixels' information can be expressed sufficiently ...
ADAPTIVE ACTIVATIONS AND SHIFT INVARIANCE IN SHALLOW CONVOLUTIONAL NEURAL NETWORKS
(2021-08-13)
Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having ...
VERIFICATION AND VALIDATION OF POWER CONVERTERS FOR USE IN FUTURE POWER SYSTEM ARCHITECTURES
(2022-05-23)
Electronics are more widely penetrating almost every area of society and as they
do, the demand to supply them with regulated power increases considerably. The scale of
the electronic power distribution systems needed ...
Improved initialization for the multi layer perceptron
(2018-05-08)
A Multilayer Perceptron (MLP) neural network is used for solving nonlinear functional problems like function approximation, classification, data processing etc. MLP neural networks are usually trained using back propagation, ...