Scientific Research Publishing

Lightweight Capsule Network Based on Weight Sharing and Top-K Routing ()

Capsule networks can effectively model the spatial hierarchical relationships among features; however, the dynamic routing mechanism introduces a large number of parameters and high computational ...
GitHub

An Architecture Combining Convolutional Neural Network (CNN) and Linear Support Vector Machine (SVM) for Image Classification

This project was inspired by Y. Tang's Deep Learning using Linear Support Vector Machines (2013). The full paper on this project may be read at arXiv.org. The experiments were conducted on a laptop ...
IEEE

Recognition of Scanned Handwritten digits using Deep Learning

Abstract: The capability of ML (Machine Learning) algorithms to recognize images of handwritten numerals is known as HDR (Handwritten Digit Recognition). Because handwritten numerals are imperfect and ...
Frontiers

Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning

Multiclass classification is of great interest for various applications, for example, it is a common task in computer vision, where one needs to categorize an image into three or more classes. Here we ...
ascopubs.org

Using Adversarial Images to Assess the Robustness of Deep Learning Models Trained on Diagnostic Images in Oncology

HealthTree Cure Hub: A Patient-Derived, Patient-Driven Clinical Cancer Information Platform Used to Overcome Hurdles and Accelerate Research in Multiple Myeloma Adversarial images represent a ...
GitHub

Meta-learning ensemble framework for image classification with convolutional neural networks

This project creates an ensemble of CNN models for the MINST, Fashion-MNIST, and CIFAR10 dataset. The predictions from the ensemble are evaluated by a CNN super-learner and a weight matrix optimized ...
Frontiers

Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

The memristor-based convolutional neural network (CNN) gives full play to the advantages of memristive devices, such as low power consumption, high integration density, and strong network recognition ...
Scientific Research Publishing

Creating a Dataset to Boost Civil Engineering Deep Learning Research and Application ()

1 Graduate Transportation Associate, Tennessee Department of Transportation, Nashville, Tennessee, USA. 2 University of Tennessee at Chattanooga, Chattanooga, Tennessee, USA. 3 Transportation Engineer ...