Mapping Knowledge Representations to Concepts: A Review and New Perspectives

• URL: http://arxiv.org/abs/2301.00189v1
• Date: Sat, 31 Dec 2022 12:56:12 GMT
• Title: Mapping Knowledge Representations to Concepts: A Review and New Perspectives
• Authors: Lars Holmberg, Paul Davidsson, Per Linde
• Abstract summary: This review focuses on research that aims to associate internal representations with human understandable concepts. We find this taxonomy and theories of causality, useful for understanding what can be expected, and not expected, from neural network explanations. The analysis additionally uncovers an ambiguity in the reviewed literature related to the goal of model explainability.
• Score: 0.6875312133832078
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The success of neural networks builds to a large extent on their ability to create internal knowledge representations from real-world high-dimensional data, such as images, sound, or text. Approaches to extract and present these representations, in order to explain the neural network's decisions, is an active and multifaceted research field. To gain a deeper understanding of a central aspect of this field, we have performed a targeted review focusing on research that aims to associate internal representations with human understandable concepts. In doing this, we added a perspective on the existing research by using primarily deductive nomological explanations as a proposed taxonomy. We find this taxonomy and theories of causality, useful for understanding what can be expected, and not expected, from neural network explanations. The analysis additionally uncovers an ambiguity in the reviewed literature related to the goal of model explainability; is it understanding the ML model or, is it actionable explanations useful in the deployment domain?

Related papers

• Explaining Deep Neural Networks by Leveraging Intrinsic Methods [0.9790236766474201]
  This thesis contributes to the field of eXplainable AI, focusing on enhancing the interpretability of deep neural networks. The core contributions lie in introducing novel techniques aimed at making these networks more interpretable by leveraging an analysis of their inner workings. Secondly, this research delves into novel investigations on neurons within trained deep neural networks, shedding light on overlooked phenomena related to their activation values.
  arXiv  Detail & Related papers  (2024-07-17T01:20:17Z)
• Opening the Black-Box: A Systematic Review on Explainable AI in Remote Sensing [51.524108608250074]
  Black-box machine learning approaches have become a dominant modeling paradigm for knowledge extraction in remote sensing. We perform a systematic review to identify the key trends in the field and shed light on novel explainable AI approaches. We also give a detailed outlook on the challenges and promising research directions.
  arXiv  Detail & Related papers  (2024-02-21T13:19:58Z)
• Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning [3.6223658572137825]
  State of the art indicates that hidden node activations can, in some cases, be interpretable in a way that makes sense to humans. We show that we can automatically attach meaningful labels from the background knowledge to individual neurons in the dense layer of a Convolutional Neural Network.
  arXiv  Detail & Related papers  (2023-08-08T02:28:50Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• Rejecting Cognitivism: Computational Phenomenology for Deep Learning [5.070542698701158]
  We propose a non-representationalist framework for deep learning relying on a novel method: computational phenomenology. We reject the modern cognitivist interpretation of deep learning, according to which artificial neural networks encode representations of external entities.
  arXiv  Detail & Related papers  (2023-02-16T20:05:06Z)
• Formal Conceptual Views in Neural Networks [0.0]
  We introduce two notions for conceptual views of a neural network, specifically a many-valued and a symbolic view. We test the conceptual expressivity of our novel views through different experiments on the ImageNet and Fruit-360 data sets. We demonstrate how conceptual views can be applied for abductive learning of human comprehensible rules from neurons.
  arXiv  Detail & Related papers  (2022-09-27T16:38:24Z)
• From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation [16.783836191022445]
  The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual predictions in form of attribution maps, global explanation techniques visualize what concepts a model has generally learned to encode.
  arXiv  Detail & Related papers  (2022-06-07T12:05:58Z)
• Human-Centered Concept Explanations for Neural Networks [47.71169918421306]
  We introduce concept explanations including the class of Concept Activation Vectors (CAV) We then discuss approaches to automatically extract concepts, and approaches to address some of their caveats. Finally, we discuss some case studies that showcase the utility of such concept-based explanations in synthetic settings and real world applications.
  arXiv  Detail & Related papers  (2022-02-25T01:27:31Z)
• 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)
• A Chain Graph Interpretation of Real-World Neural Networks [58.78692706974121]
  We propose an alternative interpretation that identifies NNs as chain graphs (CGs) and feed-forward as an approximate inference procedure. The CG interpretation specifies the nature of each NN component within the rich theoretical framework of probabilistic graphical models. We demonstrate with concrete examples that the CG interpretation can provide novel theoretical support and insights for various NN techniques.
  arXiv  Detail & Related papers  (2020-06-30T14:46:08Z)
• 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.