Towards Benchmarking Explainable Artificial Intelligence Methods

• URL: http://arxiv.org/abs/2208.12120v1
• Date: Thu, 25 Aug 2022 14:28:30 GMT
• Title: Towards Benchmarking Explainable Artificial Intelligence Methods
• Authors: Lars Holmberg
• Abstract summary: We use philosophy of science theories as an analytical lens with the goal of revealing, what can be expected, and more importantly, not expected, from methods that aim to explain decisions promoted by a neural network. By conducting a case study we investigate a selection of explainability method's performance over two mundane domains, animals and headgear. We lay bare that the usefulness of these methods relies on human domain knowledge and our ability to understand, generalise and reason.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The currently dominating artificial intelligence and machine learning technology, neural networks, builds on inductive statistical learning. Neural networks of today are information processing systems void of understanding and reasoning capabilities, consequently, they cannot explain promoted decisions in a humanly valid form. In this work, we revisit and use fundamental philosophy of science theories as an analytical lens with the goal of revealing, what can be expected, and more importantly, not expected, from methods that aim to explain decisions promoted by a neural network. By conducting a case study we investigate a selection of explainability method's performance over two mundane domains, animals and headgear. Through our study, we lay bare that the usefulness of these methods relies on human domain knowledge and our ability to understand, generalise and reason. The explainability methods can be useful when the goal is to gain further insights into a trained neural network's strengths and weaknesses. If our aim instead is to use these explainability methods to promote actionable decisions or build trust in ML-models they need to be less ambiguous than they are today. In this work, we conclude from our study, that benchmarking explainability methods, is a central quest towards trustworthy artificial intelligence and machine learning.

Related papers

• Trustworthy Conceptual Explanations for Neural Networks in Robot Decision-Making [9.002659157558645]
  We introduce a trustworthy explainable robotics technique based on human-interpretable, high-level concepts. Our proposed technique provides explanations with associated uncertainty scores by matching neural network's activations with human-interpretable visualizations.
  arXiv  Detail & Related papers  (2024-09-16T21:11:12Z)
• From Neurons to Neutrons: A Case Study in Interpretability [5.242869847419834]
  We argue that high-dimensional neural networks can learn low-dimensional representations of their training data that are useful beyond simply making good predictions. This indicates that such approaches to interpretability can be useful for deriving a new understanding of a problem from models trained to solve it.
  arXiv  Detail & Related papers  (2024-05-27T17:59:35Z)
• Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning [0.0]
  We review current and emerging knowledge-informed and brain-inspired cognitive systems for realizing adversarial defenses. Brain-inspired cognition methods use computational models that mimic the human mind to enhance intelligent behavior in artificial agents and autonomous robots.
  arXiv  Detail & Related papers  (2024-03-11T18:11:00Z)
• Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment [65.268245109828]
  We examine algorithms for conducting credit assignment in artificial neural networks that are inspired or motivated by neurobiology. We organize the ever-growing set of brain-inspired learning schemes into six general families and consider these in the context of backpropagation of errors. The results of this review are meant to encourage future developments in neuro-mimetic systems and their constituent learning processes.
  arXiv  Detail & Related papers  (2023-12-01T05:20:57Z)
• Brain-Inspired Computational Intelligence via Predictive Coding [89.6335791546526]
  Predictive coding (PC) has shown promising performance in machine intelligence tasks. PC can model information processing in different brain areas, can be used in cognitive control and robotics.
  arXiv  Detail & Related papers  (2023-08-15T16:37:16Z)
• What are the mechanisms underlying metacognitive learning? [5.787117733071415]
  We postulate that people learn this ability from trial and error (metacognitive reinforcement learning) Here, we systematize models of the underlying learning mechanisms and enhance them with more sophisticated additional mechanisms. Our results suggest that a gradient ascent through the space of cognitive strategies can explain most of the observed qualitative phenomena.
  arXiv  Detail & Related papers  (2023-02-09T18:49:10Z)
• Interpreting Neural Policies with Disentangled Tree Representations [58.769048492254555]
  We study interpretability of compact neural policies through the lens of disentangled representation. We leverage decision trees to obtain factors of variation for disentanglement in robot learning. We introduce interpretability metrics that measure disentanglement of learned neural dynamics.
  arXiv  Detail & Related papers  (2022-10-13T01:10:41Z)
• Explainability in Deep Reinforcement Learning [68.8204255655161]
  We review recent works in the direction to attain Explainable Reinforcement Learning (XRL) In critical situations where it is essential to justify and explain the agent's behaviour, better explainability and interpretability of RL models could help gain scientific insight on the inner workings of what is still considered a black box.
  arXiv  Detail & Related papers  (2020-08-15T10:11:42Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.