A Conceptual Bio-Inspired Framework for the Evolution of Artificial General Intelligence
This work addresses the challenge of developing artificial general intelligence through an evolutionary approach, but it is conceptual and incremental, lacking empirical validation.
The authors proposed a conceptual bio-inspired framework for evolving artificial general intelligence, where agents with spiking neural networks evolve in topology and learning types through environmental rewards, aiming to enable self-learning and adaptation in mutable environments.
In this work, a conceptual bio-inspired parallel and distributed learning framework for the emergence of general intelligence is proposed, where agents evolve through environmental rewards and learn throughout their lifetime without supervision, i.e., self-learning through embodiment. The chosen control mechanism for agents is a biologically plausible neuron model based on spiking neural networks. Network topologies become more complex through evolution, i.e., the topology is not fixed, while the synaptic weights of the networks cannot be inherited, i.e., newborn brains are not trained and have no innate knowledge of the environment. What is subject to the evolutionary process is the network topology, the type of neurons, and the type of learning. This process ensures that controllers that are passed through the generations have the intrinsic ability to learn and adapt during their lifetime in mutable environments. We envision that the described approach may lead to the emergence of the simplest form of artificial general intelligence.