This project aim to understad if a deep learning model is calibrated (average accuracy match average confident) using Reliability Diagram and perform a re-calibration by the training with Focal Loss.
-
Updated
Feb 21, 2023 - Jupyter Notebook
This project aim to understad if a deep learning model is calibrated (average accuracy match average confident) using Reliability Diagram and perform a re-calibration by the training with Focal Loss.
Code for "Conformal Performance Range Prediction for Segmentation Output Quality Control" accepted to MICCAI UNSURE 2024
Code for my Bachelor's thesis "Drone image and video encoding and processing using machine learning"
Conformal Off-policy Prediction
A graphical user interface (GUI) and web application to facilitate the usage of ENS-Score.
Implemented Conformal Prediction algorithm with one nearest neighbour in Python. Project involves creating artificial datasets to assess the algorithm's performance under varying noise and data distributions.
Code for "Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets", Arxiv 2024.
Machine Learning Assignment
This repository contains jupyter notebooks providing an implementation of basic Machine Learning models for regression and classification.
Conformal Bayesian Computation (CBC). This paper summarizes the theoretical foundings of the CBC, as well as it applies to 2 use-cases: classification and regression.
Conformal Bayesian Computation with Stan and Numba.
This project provides sample code for performing supervised learning.
"Improving Trustworthiness of AI Disease Severity Rating in Medical Imaging with Ordinal Conformal Prediction Sets" presented at MICCAI 2022
Implementation of the paper "CICLe: Conformal In-Context Learning for Largescale Multi-Class Food Risk Classification"
Pneumonia classification as a service
A serverless function is utilized to evaluate the divergence of a particular output from the established log-likelihood set by a language model. This function is designed to compute the log-likelihood per message. Subsequently, p-values are generated and used as a prediction interval to categorize, appropriately append, and sort LLM output
This is a small demo of Conformal Prediction given to Prof. Glenn Shafer's class in Feb-2018. Compares Conformal Prediction to plain Linear Regression using the Boston dataset from R
Add a description, image, and links to the conformal-prediction topic page so that developers can more easily learn about it.
To associate your repository with the conformal-prediction topic, visit your repo's landing page and select "manage topics."