Fast embedding-based graph classification with connections to kernels
-
Updated
May 6, 2020 - Python
Fast embedding-based graph classification with connections to kernels
Quantum kernel estimation with backend-matched IBM noise modeling, plus reproducible “Wigner’s friend” branch-transfer coherence-witness experiments executed on superconducting quantum hardware.
Interactive web application for visualizing CNN layer activations, feature maps, and Grad-CAM heatmaps. Built with FastAPI, PyTorch, and Next.js.
Interactive Streamlit app mapping PyTorch CNN activation maps (VGG16) directly to biological visual cortex regions (V1 to IT). Features live feature map extraction via forward hooks and neural heatmaps.
A comprehensive implementation and evaluation of three state-of-the-art object detection architectures: Faster R-CNN, YOLOv11n, and DETR on COCO 2017 and Pascal VOC 2012 datasets.
A deep learning project that builds and evaluates Convolutional Neural Network (CNN) models for classifying CIFAR-10 images, compares a custom CNN with ResNet-18, and applies hyperparameter tuning to improve model performance and generalization.
PQC binary classifier for HEP signal/background separation. Four implementations across Qiskit and PyQuil.
Add a description, image, and links to the feature-maps topic page so that developers can more easily learn about it.
To associate your repository with the feature-maps topic, visit your repo's landing page and select "manage topics."