What-if

Enables teams to run hypothetical scenarios to understand what features need to be tweaked to obtain desired predictions

The 'What-if' feature enables teams to run hypothetical scenarios to understand what features need to be tweaked to obtain desired predictions. Such scenarios can provide quick insights into the model to the users.

‍

Liked the content? you'll love our emails!

Thank you! We will send you newest issues straight to your inbox!

Oops! Something went wrong while submitting the form.

See how AryaXAI improves
ML Observability

Learn how to bring transparency & suitability to your AI Solutions, Explore relevant use cases for your team, and Get pricing information for XAI products.

Schedule a demo

Modern solution for ML Observability awaits

Schedule a demo

What is AryaXAI

Learn about our product →

Access Resources

Articles, Videos, Wikis and more →

Contact Us

Get to know us →

AryaXAI is a full stack ML Observability tool for mission-critical AI functions. Designed by Arya.ai, it is aimed to deliver much required common platform between stakeholders and deliver trust, transparency and auditability.

PRODUCTS

RESOURCES

COMPANY

© Copyright 2024, Lithasa Technologies Pvt. Ltd.

Internet Information Service Algorithm Recommendation Management Regulations

Generative AI Measures in China

Provisions on the Administration of Deep Synthesis of Internet-based Information Services

Artificial Intelligence and Algorithmic Fairness Initiative

Artificial Intelligence Risk Management Framework (AI RMF 1.0)

Federal Trade Commission (FTC)

President Biden's Executive Order on AI

Principles for Responsible AI

Digital India Act

Draft National Data Governance Framework Policy

National Strategy for Artificial Intelligence #AIFORALL: NITI Aayog

National Cybersecurity Reference Framework

Global Partnership on Artificial Intelligence (GPAI)

Low-Rank Adaptation (LoRA)

Multi-modal models

Mixture of experts (MoEs)

Opensource vs. Closed Source Models

Diffusion Models

Transformers Models

Vector database

Large Language Models (LLMs)

Foundation models

Chi-square test

Kolmogorov–Smirnov test (K–S test or KS test)

Wasserstein distance

Jensen-Shannon(JS) Divergence

Population Stability Index (PSI)

Kullback-Leibler (KL) divergence

Bias Monitoring

Data Monitoring

ML Observability

Regression model

Classification model

Model confidence score

Model threshold

Surrogate models

Feature Importance Store

Fairness/Bias Monitoring

Data Processing

Recall/ Sensitivity or True Positive Rate

Specificity/ True Negative Rate:

Precision-recall curve

Confusion Matrix

ROC Curves and ROC AUC