Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Advancing Explainable AI Toward Human-Like Intelligence: Forging the Path to Artificial Brain

Yongchen Zhou, Richard Jiang

TL;DR

This paper surveys the current landscape of Explainable AI (XAI) and advocates a path toward Human-Like Intelligence (HLI) by integrating neuroscience and cognitive science with AI. It catalogs a spectrum of XAI methods—feature-based, pixel-based, concept-based, surrogate, and human-centric—and discusses the challenges in explaining generative models, implementing responsible AI, and addressing ethical implications. The authors explore brain-inspired directions, including consciousness, emotion, AI personality, and biologically plausible models, and argue that progress requires neuro-AI interfaces and learning from brain mechanisms. The work emphasizes multidisciplinary collaboration to enhance interpretability, trust, and societal alignment as AI advances toward Artificial General Intelligence (AGI).

Abstract

The intersection of Artificial Intelligence (AI) and neuroscience in Explainable AI (XAI) is pivotal for enhancing transparency and interpretability in complex decision-making processes. This paper explores the evolution of XAI methodologies, ranging from feature-based to human-centric approaches, and delves into their applications in diverse domains, including healthcare and finance. The challenges in achieving explainability in generative models, ensuring responsible AI practices, and addressing ethical implications are discussed. The paper further investigates the potential convergence of XAI with cognitive sciences, the development of emotionally intelligent AI, and the quest for Human-Like Intelligence (HLI) in AI systems. As AI progresses towards Artificial General Intelligence (AGI), considerations of consciousness, ethics, and societal impact become paramount. The ongoing pursuit of deciphering the mysteries of the brain with AI and the quest for HLI represent transformative endeavors, bridging technical advancements with multidisciplinary explorations of human cognition.

Advancing Explainable AI Toward Human-Like Intelligence: Forging the Path to Artificial Brain

TL;DR

This paper surveys the current landscape of Explainable AI (XAI) and advocates a path toward Human-Like Intelligence (HLI) by integrating neuroscience and cognitive science with AI. It catalogs a spectrum of XAI methods—feature-based, pixel-based, concept-based, surrogate, and human-centric—and discusses the challenges in explaining generative models, implementing responsible AI, and addressing ethical implications. The authors explore brain-inspired directions, including consciousness, emotion, AI personality, and biologically plausible models, and argue that progress requires neuro-AI interfaces and learning from brain mechanisms. The work emphasizes multidisciplinary collaboration to enhance interpretability, trust, and societal alignment as AI advances toward Artificial General Intelligence (AGI).

Abstract

The intersection of Artificial Intelligence (AI) and neuroscience in Explainable AI (XAI) is pivotal for enhancing transparency and interpretability in complex decision-making processes. This paper explores the evolution of XAI methodologies, ranging from feature-based to human-centric approaches, and delves into their applications in diverse domains, including healthcare and finance. The challenges in achieving explainability in generative models, ensuring responsible AI practices, and addressing ethical implications are discussed. The paper further investigates the potential convergence of XAI with cognitive sciences, the development of emotionally intelligent AI, and the quest for Human-Like Intelligence (HLI) in AI systems. As AI progresses towards Artificial General Intelligence (AGI), considerations of consciousness, ethics, and societal impact become paramount. The ongoing pursuit of deciphering the mysteries of the brain with AI and the quest for HLI represent transformative endeavors, bridging technical advancements with multidisciplinary explorations of human cognition.
Paper Structure (26 sections, 3 figures, 1 table)

This paper contains 26 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. The State-of-The-Art XAI
  3. Features-Oriented Methods
  4. Pixel-Based Methods
  5. Concept Models
  6. Surrogate Models
  7. Human-Centric Methods
  8. Usability of Counterfactual Explanations
  9. Current Challenges in XAI
  10. Explainability of Generative Models
  11. Responsible AI
  12. Ethical Implications of Explanations
  13. From XAI to Artificial Brain
  14. Understanding and Mimicking Brain Functionality
  15. AI Consciousness and Cognition
  16. ...and 11 more sections

Figures (3)

  • Figure 1: The cycle of learning. As neural networks evolve by mimicking the brain, they offer insights that, in turn, illuminate our understanding of cerebral processes.
  • Figure 2: The inscrutability of generative models. Generative models, similar to black boxes, conceal the intricate processes behind their creative outputs, making their internal workings enigmatic and challenging for humans to decipher.
  • Figure 3: The evolution of artificial intelligence. The arrow's ascent reflects the dynamic growth and expanding capabilities of AI, marking key developments from basic algorithms to advanced sentient systems.