 |
VOOZH | about |
Comprehensive LLM testing suite for safety, performance, bias, and compliance, equipped with methodologies and tools to enhance the reliability and ethical integrity of models like OpenAI's GPT series for real-world applications.
Introduction to trusted AI. Learn to use fairness algorithms to reduce and mitigate bias in data and models with aif360 and explain models with aix360
Example projects for Arthur Model Monitoring Platform
This project aims to differentiate among various diseases (multiclass prediction) present in mango leaves. Various machine learning techniques were employed in this project to achieve optimal performance in a model capable of predicting multiple classes.
Introduction to simple machine learning, deep learning and geometric deep learning concepts and methods.
Fairness in data, and machine learning algorithms is critical to building safe and responsible AI systems from the ground up by design. Both technical and business AI stakeholders are in constant pursuit of fairness to ensure they meaningfully address problems like AI bias. While accuracy is one metric for evaluating the accuracy of a machine le…
LIME ile Makine Öğrenmesi Modellerini Açıklamak - Demo ResNet50 derin öğrenme modelinin görsel sınıflandırma kararlarını LIME (Local Interpretable Model-agnostic Explanations) algoritması kullanarak açıklayan ve görselleştiren Python projesi. GPU desteği ile hızlı işlem sağlar.
Comparative Analysis of Bi-Directional Long Short-Term Memory and BERT Models for Fake News Detection with Explainable AI Using Lime
This project demonstrates a machine learning pipeline using Azure ML for model optimization. It compares HyperDrive-tuned Scikit-learn Logistic Regression with Azure AutoML’s automated model selection. Includes code, documentation, and performance comparisons, showcasing Azure ML's model management and optimization capabilities.
In-depth exploration of Large Language Models (LLMs), their potential biases, limitations, and the challenges in controlling their outputs. It also includes a Flask application that uses an LLM to perform research on a company and generate a report on its potential for partnership opportunities.
A PyTorch-based deep learning extension to my PhD thesis on credit scoring of thin-file consumers.
Implementation of global methods (explain the behavior of a model as a whole) and local methods (respect to a specific decision) that allow to explain why an AI model makes its decisions.
This repository contains both writing and coding work.
React Native mobile app leveraging machine learning for real-time crop disease diagnosis and yield loss prediction.
Explainability of AI models is a difficult task which is made simpler by Cortex Certifai. It evaluates AI models for robustness, fairness, and explainability, and allows users to compare different models or model versions for these qualities. Certifai can be applied to any black-box model including machine learning models, predictive models and …
Add a description, image, and links to the ai-explainability topic page so that developers can more easily learn about it.
To associate your repository with the ai-explainability topic, visit your repo's landing page and select "manage topics."