Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 2762 for “"Convolutional Neural Networks"”.
-
Understanding convolutional neural networks
… we introduce several methods for understanding convolutional neural networks (CNNs), the class of deep learning models that is typically applied to visual data — i.e. images and videos. Our techniques span three approaches to understanding a model: 1. describing the relationship between its …
-
Counting with convolutional neural networks
In this work, we tackle the question: Can neural networks count? More precisely, given an input image with a certain number of objects, can a neural network tell how many are there? To study this, we create a synthetic dataset consisting of black and white images with variable numbers of white …
-
Gauge equivariant convolutional neural networks
… current theory of group and gauge equivariant convolutional neural networks on homogeneous spaces and general smooth manifolds, with focus on the latter, formulated from a mathematical viewpoint. We also provide a new interpretation of layers in neural networks as maps between associated …
-
Visualization of Deep Convolutional Neural Networks
… scene recognition tasks, especially after the Convolutional Neural Network (CNN) model was introduced. Although a CNN often demonstrates very good classification results, it is usually unclear how or why a classification result is achieved. The objective of this thesis is to explore several …
-
Representation Learning With Convolutional Neural Networks
… we focus on representation learning with deep neural networks for different data formats including text, 3D polygon shapes, and brain fiber tracts. First, we propose a topic-based word representation learning approach for text classification. The proposed approach takes global semantic …
-
Person Identification With Convolutional Neural Networks
… for match- ing to tackle these challenges. With Convolutional Neural Networks (CNNs), feature extraction and metric learning can be combined in a unified framework. In this work, we study two important sub-problems of person identification: cross- view person identification and visible-thermal …
-
Resiliency in Deep Convolutional Neural Networks
The enormous success and popularity of deep convolutional neural networks for object detection has prompted their deployment in various real-world applications. However, their performance in the presence of hardware faults or damage that could occur in the field has not been studied. This thesis …
-
Convolutional Neural Networks on the Edge
… on IoT data has opened up lots of opportunities. Neural networks are used to analyze the data and make sense of it by converting data into useful information in real-world applications such as speech recognition or image classification. Today, optimized neural networks found their way from the …
-
Robust classification with convolutional neural networks
… performance by using methods based on Convolutional Neural Networks (CNNs). Face image analysis requires both effective feature extraction and classifier systems. This research considers the deep learning algorithm and addresses its working for classification tasks. I shows how to …
-
Model Attack on Convolutional Neural Networks
Deep learning is a machine learning technique that enables computers to learn directly from images, text, or sound in the same way that people do. It is a key technology which enables selfdriving cars and speech recognition. In the past few years, deep learning has been successfully used in a wide …
-
WAKE DETECTION USING CONVOLUTIONAL NEURAL NETWORKS
… wakes to persist for long timescales. Artificial neural networks trained on velocity field data show promise to automate detection. We used numerical simulations to generate velocity data on wake, jet, and convective turbulence. All these forms of turbulence have similar characteristics in the …
-
Hardware Accelerator for Convolutional Neural Networks
Στην παρούσα εργασία επιχειρούμε να συζητήσουμε το θέμα των επιταχυντών για νευρωνικά δίκτυα που γίνεται αντιληπτό ως συνδετικός κρίκος ανάμεσα σε δύο πεδία της επιστήμης των υπολογιστών: τη σχεδίαση παράλληλων συστημάτων και τη σχεδίαση αλγορίθμων μηχανικής μάθησης. Το πρώτο πεδίο ερευνά τους …
-
Evolutionary Optimisation in Convolutional Neural Networks
Artificial Neural Networks (ANNs) have increased in performance in recent years and have been successfully used in many computer applications. The growth in ANNs and machine learning applications has resulted in the state-of-the-art ANNs comprising hundreds of hidden layers, which require millions …
-
Convolutional neural networks in vision neuroscience
Contains fulltext : 228249.pdf (Publisher’s version ) (Open Access)
-
Debiasing convolutional neural networks via Meta Orthogonalization
… in datasets. In this work, we focus on debiasing convolutional neural networks (CNNs), through our proposed Meta Orthogonalization algorithm. We leverage past work in debiasing word embeddings and interpretability literature to force image concepts learned by a CNN to be orthogonal to a bias …
-
Predicting Magnetization Directions Using Convolutional Neural Networks
… the use of machine learning, specifically Convolutional Neural Network (CNN), to automatically predict the magnetization direction of a magnetic source body, given a magnetic map. CNN has achieved great success in other applications such as computer vision, but has not been attempted in the …
-
FLUORESCENCE SPECTROSCOPY ANALYSIS THROUGH CONVOLUTIONAL NEURAL NETWORKS
… coefficient. In this research, we apply a convolutional neural network (CNN) to determine the diffusion coefficient of freely diffusing molecules. We construct the CNN based on our concurrent study of model identification of autoregression moving average (ARMA) time series through CNN, …
-
SuperCDMS event reconstruction using convolutional neural networks
… particle events. This thesis explores the use of Convolutional Neural Networks (CNNs) to perform this reconstruction and finds that, although they perform well, changing the noise model breaks the model and requires the neural network to be retrained. In order to mitigate this issue, a new CNN …
Page 1 of 139