Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Brain-inspired Artificial Intelligence: A Comprehensive Review

Jing Ren, Feng Xia

TL;DR

The paper addresses how neuroscience-informed design can advance AI by organizing brain-inspired ideas into physical-structure and human-behavior-inspired categories. It surveys neural architectures, learning mechanisms, attention, memory, consciousness, and creativity as foundations for PS and HB models, and reviews representative models such as CNNs, CapsNets, SNNs, memory networks, imitation learning, and reinforcement learning. It highlights applications across robotics, healthcare, emotion perception, and creative industries, detailing benefits and deployment challenges like data needs, interpretability, and ethics. The work emphasizes future directions including tighter integration with neuroscience, scalable and efficient systems, responsible and transparent AI, and the pursuit of conscious-like capabilities, aiming to accelerate the development of robust, adaptable, brain-inspired intelligent systems with real-world impact.

Abstract

Current artificial intelligence (AI) models often focus on enhancing performance through meticulous parameter tuning and optimization techniques. However, the fundamental design principles behind these models receive comparatively less attention, which can limit our understanding of their potential and constraints. This comprehensive review explores the diverse design inspirations that have shaped modern AI models, i.e., brain-inspired artificial intelligence (BIAI). We present a classification framework that categorizes BIAI approaches into physical structure-inspired and human behavior-inspired models. We also examine the real-world applications where different BIAI models excel, highlighting their practical benefits and deployment challenges. By delving into these areas, we provide new insights and propose future research directions to drive innovation and address current gaps in the field. This review offers researchers and practitioners a comprehensive overview of the BIAI landscape, helping them harness its potential and expedite advancements in AI development.

Brain-inspired Artificial Intelligence: A Comprehensive Review

TL;DR

The paper addresses how neuroscience-informed design can advance AI by organizing brain-inspired ideas into physical-structure and human-behavior-inspired categories. It surveys neural architectures, learning mechanisms, attention, memory, consciousness, and creativity as foundations for PS and HB models, and reviews representative models such as CNNs, CapsNets, SNNs, memory networks, imitation learning, and reinforcement learning. It highlights applications across robotics, healthcare, emotion perception, and creative industries, detailing benefits and deployment challenges like data needs, interpretability, and ethics. The work emphasizes future directions including tighter integration with neuroscience, scalable and efficient systems, responsible and transparent AI, and the pursuit of conscious-like capabilities, aiming to accelerate the development of robust, adaptable, brain-inspired intelligent systems with real-world impact.

Abstract

Current artificial intelligence (AI) models often focus on enhancing performance through meticulous parameter tuning and optimization techniques. However, the fundamental design principles behind these models receive comparatively less attention, which can limit our understanding of their potential and constraints. This comprehensive review explores the diverse design inspirations that have shaped modern AI models, i.e., brain-inspired artificial intelligence (BIAI). We present a classification framework that categorizes BIAI approaches into physical structure-inspired and human behavior-inspired models. We also examine the real-world applications where different BIAI models excel, highlighting their practical benefits and deployment challenges. By delving into these areas, we provide new insights and propose future research directions to drive innovation and address current gaps in the field. This review offers researchers and practitioners a comprehensive overview of the BIAI landscape, helping them harness its potential and expedite advancements in AI development.
Paper Structure (47 sections, 4 equations, 4 figures, 2 tables)

This paper contains 47 sections, 4 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Motivation
  3. Related Surveys and Novelty
  4. Contributions
  5. AI Learning from Human Brain
  6. Neural Architecture
  7. Learning Mechanism
  8. Attention and Focus
  9. Memory and Recall
  10. Consciousness
  11. Creativity and Imagination
  12. Brain-inspired AI Models
  13. Physical structure-inspired AI Models
  14. Hierarchical Models
  15. SNNs
  16. ...and 32 more sections

Figures (4)

  • Figure 1: Structure of this comprehensive review.
  • Figure 2: The process of machine unlearning. When users want their data deletion, they should be deleted from the database and it needs to remove their contribution to the already trained model.
  • Figure 3: BIAI Applications.
  • Figure 4: Differences between traditional robots and brain-inspired robots.