Real-World Super-Resolution via Kernel Estimation and Noise Injection

Code for "DeepDRR: A Catalyst for Machine Learning in Fluoroscopy-guided Procedures". https://arxiv.org/abs/1803.08606

Noise Injection Techniques provides a comprehensive exploration of methods to make machine learning models more robust to real-world bad data. This repository explains and demonstrates Gaussian noise, dropout, mixup, masking, adversarial noise, and label smoothing, with intuitive explanations, theory, and practical code examples.

NINJA: Noise Inject agent tool to expose subtle and unintended message races

This project leverages advanced machine learning algorithms to detect and classify malicious emails, focusing on spam and phishing threats. As email threats grow more sophisticated, accurate detection is critical to ensuring the security and privacy of both individuals and organizations.

Verification harness for quantum ML. A reproducible lab for stress-testing quantum models where predictive accuracy, identifiability, curvature, and robustness under noise can diverge.

Scripts to inject noise into Google's GREAT code dataset to study memorization in neural code models.

Modular anti-tracking toolkit — audit how trackable you are online and apply countermeasures. DNS leaks, metadata, browser fingerprinting, cookies, social trackers, search/social noise injection.

🔍 Enhance model robustness with noise injection techniques to tackle messy, real-world data and improve machine learning performance.

📧 Detect spam emails easily using machine learning with TF-IDF Vectorizer and Naive Bayes for accurate and efficient filtering.

Time series forecasting and classification using shared linear backbone with task-specific heads and forgetting mechanisms

📧 Detect spam emails with ease using machine learning and the Naive Bayes algorithm for fast, accurate results.