@ Intelligent Systems Lab - Ioannis Mollas
Daniele Fadda, CNR
Explainable AI
Explainable AI (XAI) investigates methods for analyzing or complementing AI models to make the internal logic and output of algorithms transparent and interpretable, making these processes humanly understandable and meaningful. Some might dispute the need for XAI, and it is true that there is no need for explainability in certain applications. This assumption may well be true in cases where the ultimate goal is the maximum performance, for example in a cat-vs-dog image classifier. This is not the case, however, when these applications concern people's lives and well-being. A system proposing a specific amount of a drug to a patient, or a system suggesting prison time for a defendant must have an element of being questionable and reasonable. Explainability of such systems will provide transparency and allow human experts to be advised, rather than blindly rely on them.
Copyright (c) 2021, N. Gkalelis, A. Goulas, D. Galanopoulos, V. Mezaris / CERTH-ITI
Asset Type
Library
ObjectGraphs
Using Objects and a Graph Convolutional Network for the Bottom-up Recognition and Explanation of Events in Video
Asset Type
Dataset
Vibration sensor measurements in a robotic wrist
A data set of 1.8 billion measurements from a mechanical wrist with three axes that can hold tools, for example, for spray painting in combination with a pump. The data set spans six months in 1-second intervals.
Asset Type
Docker container
ISIC CNN
Deep Neural Network trained for the classification of dermoscopic images into nine categories.
Asset Type
Docker container
Clingo Answer Set Solver
State-of-the-art solver for logic programming under the answer set semantics.
@ Intelligent Systems Lab
@ Intelligent Systems Lab - Ioannis Mollas
Asset Type
Jupyter Notebook
LioNets
LioNets: Local Interpretations Of Neural Networks through Penultimate Layer Decoding
Daniele Fadda, CNR
Asset Type
Jupyter Notebook
LORE
LORE (LOcal Rule-based Explanations) is a model-agnostic explanator for tabular data
@ Intelligent Systems Lab - Ioannis Mollas
Asset Type
Jupyter Notebook
LioNets on Time Series
LioNets technique applied to the Turbofan Engine Degradation Simulation dataset (time-series data) LioNets on Time Series
@ Intelligent Systems Lab - Ioannis Mollas
Asset Type
Docker container
LioNets v2
A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information
@ Intelligent Systems Lab - Ioannis Hatziarapis
Asset Type
Executable
LionForests Bot
Interactive dialogue between user-machine learning model via explanations
