monte-carlo-dropout

A pytorch implementation of MCDO(Monte-Carlo Dropout methods)

All the material needed to use MC-CP and the Adaptive MC Dropout method

Hybrid CNN-Transformer model for automated exoplanet transit detection on NASA Kepler light curves. Features dual scale CNN branches, Transformer based sequence modelling, Grad CAM + SHAP + attention explainability, and Monte Carlo Dropout uncertainty quantification. 5 fold cross validated with baseline comparisons.

Uncertainty Estimation Using Deep Neural Network and Gradient Boosting Methods

Bayesian deep learning experiments

PyTorch-native Bayesian neural networks for uncertainty quantification in deep learning

An experimental Python package for learning Bayesian Neural Network.

PyTorch implementation of landmark-based facial expression recognition using Spatio-Temporal BiLinear Networks (ST-BLN)

An NLP Model used for automated assignment of bug reports to the relevant engineering team. Utilizes a novel confidence bounding approach - Monte Carlo Dropout, and assigns underconfident predictions to a queue for human review. Built for Pegasystems Inc.

Hybrid Uncertainty Quantification for Bioactivity Assessment

GraphGE: Uncertainty-aware fraud detection on Bitcoin transactions using GraphSAGE. Implements Bayesian uncertainty quantification via Monte Carlo Dropout, class-imbalance mitigation, and selective prediction with calibrated probabilities (ECE < 0.05).

Comparison of a network implemented via Variational Inference with the same network implemented via Monte Carlo Dropout

(Forked Version) Experiments used in "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning"

Official implementation of "Uncertainty-Guided Semi-Supervised Learning for Safe Medical Image Classification".

GUI for analyzing deep learning models with uncertainty in predictions

monitor.ai: Non-intrusive monitoring for FDA-approved medical AI, helping healthcare organizations ensure safety and compliance without modifying validated models.

Loto6 lottery number prediction with BiLSTM + Monte Carlo Dropout (educational use)

A hybrid deep learning framework for automated diabetic retinopathy detection combining EfficientNetB0 with Swin Transformer attention mechanisms. Features Bayesian uncertainty quantification through Monte Carlo Dropout, explainable AI visualizations with Grad-CAM, and specialized preprocessing techniques.

RAG system with Bayesian uncertainty quantification using Beta priors and Monte Carlo Dropout