Biological plastic neural networks are systems of extraordinary computational capabilities shaped by evolution, development, and lifetime learning. The interplay of these elements leads to the emergence of adaptive behavior and intelligence. Inspired by such intricate natural phenomena, Evolved Plastic Artificial Neural Networks (EPANNs) use simulated evolution in-silico to breed plastic neural networks with a large variety of dynamics, architectures, and plasticity rules: these artificial systems are composed of inputs, outputs, and plastic components that change in response to experiences in an environment. These systems may autonomously discover novel adaptive algorithms, and lead to hypotheses on the emergence of biological adaptation. EPANNs have seen considerable progress over the last two decades. Current scientific and technological advances in artificial neural networks are now setting the conditions for radically new approaches and results. In particular, the limitations of hand-designed networks could be overcome by more flexible and innovative solutions. This paper brings together a variety of inspiring ideas that define the field of EPANNs. The main methods and results are reviewed. Finally, new opportunities and developments are presented.
We really know of only a single intelligence abstraction approach that truly does work, the one based on the interconnection of spatio-temporal signal integrators in a vast graph: Neural Network . We also know of only one method that was able to generate such abstracted intelligence: Evolution . The proof that this abstraction and this generative method works is us, you and I, the result of billions of years of trial and error. There is nothing mystical about the human brain, it is but a vast graph of signal integrators, carved out in flesh through billions of years of evolution. In this paper we discuss: intelligence abstraction based on neural networks, complex-valued artificial neurons and their computational potential to be equivalent to biological ones, the approaches that could result in the generation of such intelligent graphs of interconnected complex-valued neurons, an architecture of infomorphs whose brains are complex-valued neural substrates, and why an ALife approach on high enough granularity level is our best chance of evolving organisms that are truly intelligent.
Complex environments provide structured yet variable sensory inputs. To best exploit information from these environments, organisms must evolve the ability to correctly anticipate consequences of unknown stimuli, and act on these predictions. We propose an evolutionary path for neural networks, leading an organism from reactive behavior to simple proactive behavior and from simple proactive behavior to induction-based behavior. Through in-vitro and in-silico experiments, we define the minimal conditions necessary in a network with spike-timing dependent plasticity for the organism to go from reactive to proactive behavior. Our results support the existence of small evolutionary steps and four necessary conditions allowing embodied neural networks to evolve predictive and inductive abilities from an initial reactive strategy. We extend these conditions to more general structures.
A major goal for AI is to allow users to interact with agents that learn in real time, making new kinds of interactive simulations, training applications, and digital entertainment possible. This paper describes such a learning technology, called real-time NeuroEvolution of Augmenting Topologies (rtNEAT), and describes how rtNEAT was used to build the NeuroEvolving Robotic Operatives (NERO) video game. This game represents a new genre of machine learning games where the player trains agents in real time to perform challenging tasks in a virtual environment. Providing laymen the capability to effectively train agents in real time with no prior knowledge of AI or machine learning has broad implications, both in promoting the field of AI and making its achievements accessible to the public at large.
A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately, canonical methods are very prone to catastrophic forgetting (CF) - the act of overwriting previous knowledge about a task when learning a new task. Recent efforts have developed techniques for overcoming CF in learning systems, but no attempt has been made to apply these new techniques to evolutionary systems. This research presents a novel technique, weight protection, for reducing CF in evolutionary systems by adapting a method from learning systems. It is used in conjunction with other evolutionary approaches for overcoming CF and is shown to be effective at alleviating CF when applied to a suite of reinforcement learning tasks. It is speculated that this work could indicate the potential for a wider application of existing learning-based approaches to evolutionary systems and that evolutionary techniques may be competitive with or better than learning systems when it comes to reducing CF.