Triple equivalence for the emergence of biological intelligence
Characterising the intelligence of biological organisms is challenging. This work considers intelligent algorithms developed evolutionarily within neural systems. Mathematical analyses unveil a natural equivalence between canonical neural networks, variational Bayesian inference under a class of partially observable Markov decision processes, and differentiable Turing machines, by showing that they minimise the shared Helmholtz energy. Consequently, canonical neural networks can biologically plausibly equip Turing machines and conduct variational Bayesian inferences of external Turing machines in the environment. Applying Helmholtz energy minimisation at the species level facilitates deriving active Bayesian model selection inherent in natural selection, resulting in the emergence of adaptive algorithms. In particular, canonical neural networks with two mental actions can separately memorise transition mappings of multiple external Turing machines to form a universal machine. These propositions were corroborated by numerical simulations of algorithm implementation and neural network evolution. These notions offer a universal characterisation of biological intelligence emerging from evolution in terms of Bayesian model selection and belief updating.
Code (1)
Tasks
Bayesian InferenceModel SelectionSimilar Papers 제목 키워드 기반
Model of human cognition
The development of large language models (LLMs) is limited by a lack of explainability, the absence of a unifying theory, and prohibitive operational costs. We propose a neuro-theoretical framework for the emergence of i…
Digital twin brain: a bridge between biological intelligence and artificial intelligence
In recent years, advances in neuroscience and artificial intelligence have paved the way for unprecedented opportunities for understanding the complexity of the brain and its emulation by computational systems. Cutting-e…
A Conceptual Bio-Inspired Framework for the Evolution of Artificial General Intelligence
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 life…
Self-LearningSelf-Supervised LearningAdaptive patch foraging in deep reinforcement learning agents
Patch foraging is one of the most heavily studied behavioral optimization challenges in biology. However, despite its importance to biological intelligence, this behavioral optimization problem is understudied in artific…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Moving boundaries: An appreciation of John Hopfield
The 2024 Nobel Prize in Physics was awarded to John Hopfield and Geoffrey Hinton, "for foundational discoveries and inventions that enable machine learning with artificial neural networks." As noted by the Nobel committe…