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 ...
Hacker

How to Configure Experiments With Hydra - From an ML Enginner Perspective

Machine learning experiments require extensive parametrization, including optimizer parameters, network architecture, and data augmentation. However, we strive for concise, readable code instead of a ...
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 ...
GitHub

The MNIST-1D Dataset

Most machine learning models get around the same ~99% test accuracy on MNIST. Our dataset, MNIST-1D, is 100x smaller (default sample size: 4000+1000; dimensionality: 40) and does a better job of ...
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 ...