Popular GitHub Repositories for Least Confidence

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

A library for differentiable nonlinear optimization

ARCH models in Python

UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

End-to-end Lane Detection for Self-Driving Cars (ICCV 2019 Workshop)

Python package for conformal prediction

Learn fast, scalable, and calibrated measures of uncertainty using neural networks!

Intelligently optimizes technical indicators and optionally selects the least intercorrelated for use in machine learning models

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/

? Out-of-Distribution Detection with PyTorch

A package for statistically rigorous scientific discovery using machine learning. Implements prediction-powered inference.

Confidence and Byt5 - based geotagging model predicting coordinates from text alone.

Official Implementation for the "Conffusion: Confidence Intervals for Diffusion Models" paper.

This project walks through how you can create recommendations using Apache Spark machine learning. There are a number of jupyter notebooks that you can run on IBM Data Science Experience, and there a live demo of a movie recommendation web application you can interact with. The demo also uses IBM Message Hub (kafka) to push application events to topic where they are consumed by a spark streaming job running on IBM BigInsights (hadoop).

[Materials & Design 2024] A Bayesian global optimization package for material design ｜ Adaptive Learning | Active Learning

The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"

We start a company-name recognition task with a small scale and low quality training data, then using skills to enhanced model training speed and predicting performance with least artificial participation. The methods we use involve lite pre-training models such as Albert-small or Electra-small with financial corpus, knowledge of distillation and multi-stage learning. The result is that we improve the recall rate of company names recognition task from 0.73 to 0.92 and get 4 times as fast as BERT-Bilstm-CRF model.

Outlier Exposure with Confidence Control for Out-of-Distribution Detection

Support vector machines (SVMs) and related kernel-based learning algorithms are a well-known class of machine learning algorithms, for non-parametric classification and regression. liquidSVM is an implementation of SVMs whose key features are: fully integrated hyper-parameter selection, extreme speed on both small and large data sets, full flexibility for experts, and inclusion of a variety of different learning scenarios: multi-class classification, ROC, and Neyman-Pearson learning, and least-squares, quantile, and expectile regression.

PyTorch Code for running various time series models for different time stamps and confidence intervals for Solar Irradiance prediction.