“…The ANN therefore defines the cell next state by processing the local information of its nearest neighbors. NCA have been successfully used to grow and replicate CA shapes and structures with neuroevolution (Nichele et al ., 2017) and with differentiable learning (Mordvintsev et al ., 2020), to produce self-organising textures (Niklasson et al ., 2021), to grow 3D artifacts (Sudhakaran et al ., 2021), for regenerating soft robots (Horibe et al ., 2021), and for controlling reinforcement learning agents (Variengien et al ., 2021).…”
Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and/or when high expressive power is desirable. Pruning (removing neurons or connections) reduces the complexity of the ANN, thus increasing its energy efficiency, and has been reported to improve the generalization capability, in some cases. In addition, it is well-known that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this study, we consider the evolutionary optimization of neural controllers for the case study of Voxel-based soft robots, a kind of modular, bio-inspired soft robots, applying pruning during fitness evaluation. For a locomotion task, and for centralized as well as distributed controllers, we experimentally characterize the effect of different forms of pruning on after-pruning effectiveness, life-long effectiveness, adaptability to new terrains, and behavior. We find that incorporating some forms of pruning in neuroevolution leads to almost equally effective controllers as those evolved without pruning, with the benefit of higher robustness to pruning. We also observe occasional improvements in generalization ability.
“…The ANN therefore defines the cell next state by processing the local information of its nearest neighbors. NCA have been successfully used to grow and replicate CA shapes and structures with neuroevolution (Nichele et al ., 2017) and with differentiable learning (Mordvintsev et al ., 2020), to produce self-organising textures (Niklasson et al ., 2021), to grow 3D artifacts (Sudhakaran et al ., 2021), for regenerating soft robots (Horibe et al ., 2021), and for controlling reinforcement learning agents (Variengien et al ., 2021).…”
Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and/or when high expressive power is desirable. Pruning (removing neurons or connections) reduces the complexity of the ANN, thus increasing its energy efficiency, and has been reported to improve the generalization capability, in some cases. In addition, it is well-known that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this study, we consider the evolutionary optimization of neural controllers for the case study of Voxel-based soft robots, a kind of modular, bio-inspired soft robots, applying pruning during fitness evaluation. For a locomotion task, and for centralized as well as distributed controllers, we experimentally characterize the effect of different forms of pruning on after-pruning effectiveness, life-long effectiveness, adaptability to new terrains, and behavior. We find that incorporating some forms of pruning in neuroevolution leads to almost equally effective controllers as those evolved without pruning, with the benefit of higher robustness to pruning. We also observe occasional improvements in generalization ability.
“…Cellular automata have been used to create realistic buildings with a basic design for the interior volume [37]. Neural cellular automata have been used to create structures such caves, buildings, and trees with increasing complexity and ability to regenerate and repair themselves [38]. Generation of the world itself has also been researched through works such as World-GAN [39] which attempts to address the shortcomings of the static world generator bundled with Minecraft through generative adversarial networks.…”
This paper proposes a procedural content generator which evolves Minecraft buildings according to an open-ended and intrinsic definition of novelty. To realize this goal we evaluate individuals' novelty in the latent space using a 3D autoencoder, and alternate between phases of exploration and transformation. During exploration the system evolves multiple populations of CPPNs through CPPN-NEAT and constrained novelty search in the latent space (defined by the current autoencoder). We apply a set of repair and constraint functions to ensure candidates adhere to basic structural rules and constraints during evolution. During transformation, we reshape the boundaries of the latent space to identify new interesting areas of the solution space by retraining the autoencoder with novel content. In this study we evaluate five different approaches for training the autoencoder during transformation and its impact on populations' quality and diversity during evolution. Our results show that by retraining the autoencoder we can achieve better open-ended complexity compared to a static model, which is further improved when retraining using larger datasets of individuals with diverse complexities.
“…Figure 6.Neural CAs have also been applied to the regeneration of Minecraft entities. In this work Sudhakaran, 2021 growing, the authors’ formulation enabled the regeneration of not only Minecraft buildings, trees, but also simple functional machines in the game such as worm-like creatures that can even regenerate into two distinct creatures when cut in half.…”
Section: Collective Intelligence For Deep Learningmentioning
confidence: 99%
“…This approach is also applicable outside of pure generative domains, and can also be applied to the construction of artificial agents in active environments such as Minecraft. (Sudhakaran et al 2021) trained neural CAs to grow complex entities from Minecraft such as castles, apartment blocks, and trees, some of which are composed of thousands of blocks. Aside from regeneration, their system is able to regrow parts of simple functional machines (such as a virtual creature in the game), and they demonstrate a morphogenetic creature grow into two distinct creatures when cut in half in the virtual world (see Figure 6).…”
Section: Collective Intelligence For Deep Learningmentioning
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 practitioners 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. Collective behavior, commonly observed in nature, tends to produce systems that are robust, adaptable, and have less rigid assumptions about the environment configuration. Collective intelligence, as a field, studies the group intelligence that emerges from the interactions of many individuals. Within this field, ideas such as self-organization, emergent behavior, swarm optimization, and cellular automata were developed to model and explain complex systems. 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 capabilities. We hope this review can serve as a bridge between the complex systems and deep learning communities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
