In biological evolution complex neural structures grow from a handful of
cellular ingredients. As genomes in nature are bounded in size, this complexity
is achieved by a growth process where cells communicate locally to decide
whether to differentiate, proliferate and connect with other cells. This
self-organisation is hypothesized to play an important part in the
generalisation, and robustness of biological neural networks. Artificial neural
networks (ANNs), on the other hand, are traditionally optimized in the space of
weights. Thus, the benefits and challenges of growing artificial neural
networks remain understudied. Building on the previously introduced Neural
Developmental Programs (NDP), in this work we present an algorithm for growing
ANNs that solve reinforcement learning tasks. We identify a key challenge:
ensuring phenotypic complexity requires maintaining neuronal diversity, but
this diversity comes at the cost of optimization stability. To address this, we
introduce two mechanisms: (a) equipping neurons with an intrinsic state
inherited upon neurogenesis; (b) lateral inhibition, a mechanism inspired by
biological growth, which controlls the pace of growth, helping diversity
persist. We show that both mechanisms contribute to neuronal diversity and
that, equipped with them, NDPs achieve comparable results to existing direct
and developmental encodings in complex locomotion tasks

该研究探讨了通过细胞间的局部通信和自组织来实现神经网络的生长过程，引入了两种机制以确保保持神经元多样性，同时解决了优化稳定性和神经元多样性之间的矛盾。实验结果表明，通过这两种机制，神经发育程序在复杂运动任务中取得了与现有编码方式相当的结果。

成长中的人工神经网络控制：神经元多样性的作用

Growing Artificial Neural Networks for Control: the Role of Neuronal  Diversity

Recent advances in theoretical biology suggest that basal cognition and
sentient behaviour are emergent properties of in vitro cell cultures and
neuronal networks, respectively. Such neuronal networks spontaneously learn
structured behaviours in the absence of reward or reinforcement. In this paper,
we characterise this kind of self-organisation through the lens of the free
energy principle, i.e., as self-evidencing. We do this by first discussing the
definitions of reactive and sentient behaviour in the setting of active
inference, which describes the behaviour of agents that model the consequences
of their actions. We then introduce a formal account of intentional behaviour,
that describes agents as driven by a preferred endpoint or goal in latent
state-spaces. We then investigate these forms of (reactive, sentient, and
intentional) behaviour using simulations. First, we simulate the aforementioned
in vitro experiments, in which neuronal cultures spontaneously learn to play
Pong, by implementing nested, free energy minimising processes. The simulations
are then used to deconstruct the ensuing predictive behaviour, leading to the
distinction between merely reactive, sentient, and intentional behaviour, with
the latter formalised in terms of inductive planning. This distinction is
further studied using simple machine learning benchmarks (navigation in a grid
world and the Tower of Hanoi problem), that show how quickly and efficiently
adaptive behaviour emerges under an inductive form of active inference.

最近理论生物学的进展表明，体外细胞培养和神经网络分别是基础认知和有感知行为的新兴属性。本文通过自由能原理的视角对这种自组织现象进行了描述，并通过模拟研究了反应性、有感知性和有意图性的行为形式，证明了在归纳推理的主动推断下自适应行为的快速高效的产生。

主动推理和有意行为

Active Inference and Intentional Behaviour

This monograph attempts a theory of every 'thing' that can be distinguished
from other things in a statistical sense. The ensuing statistical
independencies, mediated by Markov blankets, speak to a recursive composition
of ensembles (of things) at increasingly higher spatiotemporal scales. This
decomposition provides a description of small things; e.g., quantum mechanics -
via the Schrodinger equation, ensembles of small things - via statistical
mechanics and related fluctuation theorems, through to big things - via
classical mechanics. These descriptions are complemented with a Bayesian
mechanics for autonomous or active things. Although this work provides a
formulation of every thing, its main contribution is to examine the
implications of Markov blankets for self-organisation to nonequilibrium
steady-state. In brief, we recover an information geometry and accompanying
free energy principle that allows one to interpret the internal states of
something as representing or making inferences about its external states. The
ensuing Bayesian mechanics is compatible with quantum, statistical and
classical mechanics and may offer a formal description of lifelike particles.

提出了一种从统计意义上区分事物的理论，着重考察了马尔可夫毛毯对于自组织至非平衡定态的影响，并提供了一种贝叶斯力学用于自主或活动的事物，该理论涵盖量子、统计和经典力学，并可能提供生命粒子的形式化描述。