We show that a model owner can artificially introduce uncertainty into their model and provide a corresponding detection mechanism.
-
Updated
Jun 2, 2025 - Jupyter Notebook
We show that a model owner can artificially introduce uncertainty into their model and provide a corresponding detection mechanism.
Bayesian inference and model selection, Kalman and particle filters, Gibbs sampling, rejection sampling, Metropolis-Hastings
I submitted this paper to Interspeech 2018. The paper was not accepted. The reviewer comments are included in the repo.
API service providing 1,000+ creative rejection responses. Node.js/Express with MCP server for Claude Desktop. Because saying no apparently requires architecture.
Code library for the DRMD framework from 'DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift'.
Checks if a Promise is resolved or rejected asynchronously
Code for our paper analyzing the looseness of the upper bound on selective classification performance.
A Guzzle middleware to log request and responses automatically
Add a description, image, and links to the rejection topic page so that developers can more easily learn about it.
To associate your repository with the rejection topic, visit your repo's landing page and select "manage topics."