Probabilistic Machine Learning for Finance and Investing: A Primer to Generative AI with Python

Code for the paper "Getting a CLUE: A Method for Explaining Uncertainty Estimates"

Machine learning models for estimating aleatoric and epistemic uncertainty with evidential and ensemble methods.

NOMU: Neural Optimization-based Model Uncertainty

[ACL 2025] Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?.

Epistemic AlphaZero utilizes uncertainty to explore and learn even when AlphaZero gets stuck.

This repository contains a demontstration of how to build, train and evaluate a neural network capable of measuring epistemic uncertainty as proposed by the authors of Evidential Deep Learning to Quantify Classification Uncertainty

Decoder-only LLM with integrated epistemic tomography. Knows what it doesn't know.

A framework for mapping the internal geometry of transformer representations using angular projection, neuron-level modulation, and epistemically grounded prompts. Based on and extending Bird's original Spotlight Resonance Method (SRM).

Implementation of Epistemic Time-Dilation MAPPO (ETD-MAPPO). A compute-aware MARL framework where agents autonomously modulate their execution frequency based on uncertainty to reduce inference overhead.

Energy production forecasting ⚡ with PoC of Bayesian Neural Network 🎲

Uncertainty quantification and out-of-distribution detection using surjective normalizing flows

Work as part of ANL summer 2020 research on uncertainity quanitification methods in graph neural networks

Generalized Automatic Pipeline for inspecting and fixing uncertainties in your data

A Python-based tutorial on quantifying epistemic uncertainty from sparse literature data. Compares Interval Analysis, Probabilistic Mixture Models, and Dempster-Shafer Evidence Theory using a Battery GWP case study.

Limits of Acceptability with DREAM algorithm: MATLAB and Python code

A generative neural network approach to uncertainty and risk-return analysis in mineral prospectivity modelling

Original implementation of the EMD (empirical model discrepancy) model comparison criterion

Code for the ICASSP'19 submission "Modelling Sample Informativeness for Deep Affective Computing".

AI research for bias mitigation and truth verification - building fair, transparent systems that combat misinformation while ensuring equitable outcomes across all demographics.