DIANNA

Deep Insight And Neural Network Analysis, DIANNA is the only Explainable AI, XAI library for scientists supporting Open Neural Network Exchange, ONNX - the de facto standard models format.

21
mentions
12
contributors
Get started
1672 commitsLast commit ≈ 1 week ago48 stars13 forks

Cite this software

What DIANNA can do for you

  • Provides an easy-to-use interface for non (X)AI experts
  • Implements well-known XAI methods (LIME, RISE and Kernal SHAP) chosen by systematic and objective evaluation criteria
  • Supports the de-facto standard of neural network models - ONNX
  • Supports images, text, time series, and tabular data modalities and some support for embeddings in a related package
  • Comes with simple intuitive image, text, time series, and tabular benchmarks, so can help you with your XAI research
  • Scientific use-cases tutorials
  • Easily extendable to other XAI methods

Modern scientific challenges are often tackled with (Deep) Neural Networks (DNN). Despite their high predictive accuracy, DNNs lack inherent explainability. Many scientists do not harvest DNNs power because of lack of trust and understanding of their working. Meanwhile, the eXplainable AI (XAI) research offers some post-hoc (after training) interpretability methods that provide insight into the DNN reasoning by quantifying the relevance of individual features (image pixels, words in text, etc.) concerning the prediction. These relevance heatmaps indicate how the network has reached its decision directly in the input modality (images, text, speech etc.) of the scientific data. Representing visually the captured knowledge by the AI system can become a source of scientific insights. There are many Open Source Software (OSS) implementations of these methods, alas, supporting a single DNN format, while standards like Open Neural Network eXchange (ONNX) exist. The libraries are known mostly by the AI experts. For the adoption by the wide scientific community, understanding of the XAI methods, and well-documented and standardized OSS are needed. The DIANNA library supports the best XAI methods in the context of scientific usage providing their OSS implementation based on the ONNX standard and demonstrations on benchmark datasets. DIANNA supports images, text, time-series, tabular data and some embeddings support. DIANNA also comes with scientific use-casse tutorials about the use of XAI in different scientific domains: astronomy, climate, social sciences (law) and soon in geo-sciences.

Logo of DIANNA
Keywords
Programming languages
  • Jupyter Notebook 93%
  • Python 7%
  • TeX 1%
License
</>Source code

Participating organisations

Natural Sciences & Engineering
Natural Sciences & Engineering
Netherlands eScience Center
SURF

Reference papers

Mentions

How to find your Artificial Intelligence explainer

Author(s): Elena Ranguelova
Published in 2022

Testimonials

DIANNA is easy to implement into my codes. It provides various methods for heat maps. DIANNA is pretty flexible as it does not require specific kinds of models or data.
Climate researcher, Lorennz workshop 2022
What I like about DIANNA is the logo ;-), that it has a very easy interface, it is model agnostic and supports various methods and auto-tuning of parameters.
Sem Vijverberg, Vrije Universiteit Amsterdam
Fast, easy to use, comprehensive, nice visualizations.
Philine Bommer, XAI researcher, Technische Universität Berlin

Contributors

Elena Ranguelova
Elena Ranguelova
Project lead
Netherlands eScience Center
Christiaan Meijer
Scrum master, developer
Netherlands eScience Center
Yang Liu
Yang Liu
Developer
Netherlands eScience Center
Pranav Chandramouli
Pranav Chandramouli
Developer
Netherlands eScience Center
Leon Oostrum
Leon Oostrum
Developer
Netherlands eScience Center
Fakhereh Alidoost
Fakhereh Alidoost
Laura Ootes
Laura Ootes
Developer
Netherlands eScience Center
GC
Giulia Crocioni
Developer
Netherlands eScience Center
Patrick Bos
Developer, advisor
Netherlands eScience Center
Rena Bakhshi
Programme manager
Netherlands eScience Center

Related projects

Explainable Embeddings

What is happening in your machine-learned embedded spaces?

Updated 3 hours ago
In progress

AI4S2S

A high-level python package integrating expert knowledge and artificial intelligence to boost (sub) seasonal forecasting

Updated 1 week ago
In progress

DIANNA - Deep Insight and Neural Networks Analysis

Explainable AI tool for scientists

Updated 5 months ago
In progress

Explainable AI for Geo

XAI4GEO

Updated 1 week ago
Finished

The nature of EU rules: strict and detailed, or lacking bite?

Updated 21 months ago
Finished

Understanding visually grounded spoken language via multi-tasking

An alternative approach for intelligent systems to understand human speech

Updated 20 months ago
Finished

eScience Technology to Boost Quantum Dot Energy Conversion

More efficient lighting and solar energy conversion devices

Updated 24 months ago
Finished

Related software

Explainable embeddings

EX

Experiments with regard to explanation of embedded spaces and multi modal models.

Updated 25 months ago
2