[Paper Review] Brain-inspired Artificial Intelligence: A Comprehensive Review

Jing Ren, Feng Xia|arXiv (Cornell University)|Aug 27, 2024

EEG and Brain-Computer Interfaces5 citations

TL;DR

A comprehensive survey categorizing Brain-Inspired AI (BIAI) into physical-structure and human-behavior inspired models, detailing knowledge from neuroscience, applications, challenges, and future directions.

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.

Motivation & Objective

• Introduce how neuroscience and human behavior inform AI system design.
• Provide a dual-category taxonomy of BIAI: physical structure-inspired and human behavior-inspired models.
• Discuss real-world applications, benefits, deployment challenges, and implications for ethics and interpretability.
• Identify open problems and propose future research directions to advance BIAI.

Proposed method

• Survey literature on neuroscience-informed AI and human behavior-inspired learning mechanisms.
• Propose a two-category framework (physical structure-inspired vs. human behavior-inspired) for organizing BIAI approaches.
• Summarize representative models and their brain-inspired mechanisms (learning, attention, memory, etc.).
• Discuss applications across robotics, healthcare, emotion perception, and creative content generation.
• Highlight challenges such as interpretability, scalability, and alignment with brain principles, and outline future directions.

Experimental results

Research questions

• RQ1 What is BIAI and how does it differ from general AI?
• RQ2 What brain-inspired sources (neural architecture, learning, attention, memory, cognition, creativity) can inform AI model design?
• RQ3 What categories of BIAI models exist and what are their strengths and limitations?
• RQ4 Which real-world domains can benefit from BIAI and what deployment challenges arise?
• RQ5 What are the major open problems and promising directions for future BIAI research?

Key findings

• BIAI integrates principles from neural architecture, learning mechanisms, attention, memory, cognition, and creativity.
• BIAI models are organized into physical structure-inspired and human behavior-inspired approaches.
• BIAI has potential advantages in adaptability, generalization, and interpretability over traditional AI.
• Applications span robotics, healthcare, emotion perception, and content generation, with deployment challenges highlighted.
• The paper outlines open problems and future directions to advance BIAI research and practice.