Collective Intelligence for Deep Learning: A Survey of Recent Developments

Abstract

In the past decade, we have witnessed the rise of deep learning to dominate the field of artificial intelligence. Advances in artificial neural networks alongside corresponding advances in hardware accelerators with large memory capacity, together with the availability of large datasets enabled researchers and practitioners alike to train and deploy sophisticated neural network models that achieve state-of-the-art performance on tasks across several fields spanning computer vision, natural language processing, and reinforcement learning. However, as these neural networks become bigger, more complex, and more widely used, fundamental problems with current deep learning models become more apparent. State-of-the-art deep learning models are known to suffer from issues that range from poor robustness, inability to adapt to novel task settings, to requiring rigid and inflexible configuration assumptions. Ideas from collective intelligence, in particular concepts from complex systems such as self-organization, emergent behavior, swarm optimization, and cellular systems tend to produce solutions that are robust, adaptable, and have less rigid assumptions about the environment configuration. It is therefore natural to see these ideas incorporated into newer deep learning methods. In this review, we will provide a historical context of neural network research's involvement with complex systems, and highlight several active areas in modern deep learning research that incorporate the principles of collective intelligence to advance its current capabilities. To facilitate a bi-directional flow of ideas, we also discuss work that utilize modern deep learning models to help advance complex systems research. We hope this review can serve as a bridge between complex systems and deep learning communities to facilitate the cross pollination of ideas and foster new collaborations across disciplines.

Evolving Modular Soft Robots without Explicit Inter-Module Communication using Local Self-Attention

“…The concept of modularity appears also in the AL and machine learning communities, most noticeably in the area of neuroevolution and CA [26]. Indeed, we are witnessing a surge in works that incorporate these ideas into modular robots.…”

Social Neuro AI: Social Interaction as the "dark matter" of AI

“…In the last few years, part of the AI community has already started demonstrating that these problems can be alleviated by mechanisms that allow for social learning Jaques [2019], Ndousse [2021], Lee et al [2021]. More in general, concepts from complex systems such as selforganization, emergent behavior, swarm optimization and cellular systems suggest that collective intelligence could produce more robust and flexible solutions in AI, with higher sample efficiency and higher generalization Ha and Tang [2021]. In the following sections, we argue that to exploit all benefits that social learning can offer, more focus on biological plausibility, social embodiment and temporal dynamics is needed.…”

EvoJAX: Hardware-Accelerated Neuroevolution

“…Neural networks are a promising approach for modeling complex systems [8,18], and neuroevolution has made great progress in developing methods for evolving neural networks to solve a wide set of (often non-differentiable) problems. Evolution-based methods have been shown to find state-of-the-art solutions for reinforcement learning (RL) [12,21,24].…”