The optimal allocation might depend on the width of the bottleneck.

Bio-inspired design is often used in autonomous UAV navigation due to the capacity of biological systems for flight and obstacle avoidance despite limited sensory and computational capabilities. In particular, honeybees mainly use the sensory input of optic flow, the apparent motion of objects in their visual field, to navigate cluttered environments. In our work, we train a Reinforcement Learning agent to navigate a tunnel with obstacles using only optic flow as sensory input. We inspect the attention patterns of trained agents to determine the regions of optic flow on which they primarily base their motor decisions. We find that agents trained in this way pay most attention to regions of discontinuity in optic flow, as well as regions with large optic flow magnitude. The trained agents appear to navigate a cluttered tunnel by avoiding the obstacles that produce large optic flow, while maintaining a centered position in their environment, which resembles the behavior seen in flying insects. This pattern persists across independently trained agents, which suggests that this could be a good strategy for developing a simple explicit control law for physical UAVs.

Recent advances in artificial intelligence (AI) research have sparked renewed controversy as to whether machines can be sentient. One commonly acknowledged problem is that we lack a broad consensus on how to define the term'sentience'. Our goal here is to develop a workable approach to the concept of'sentience' - which we call functional sentience - for AI research and to discuss its possible implementations. This approach seeks to bridge the gap between philosophical debates and practical AI system design, grounding the concept in computational frameworks that are directly applicable to AI development. An apparent dilemma is that authors are often either defining sentience in metaphysical terms (using non-empirical concepts that go beyond normal science) [1, 2] or are defining it in terms of relatively trivial functional processes, e.g. by stipulating that sentience or consciousness is just to make perceptual information globally available within the system [3]. The former is beyond the scope of our present discussion. For the latter, the relevant mechanisms are easy to implement, e.g.

This paper proposes a novel theoretical model to explain how the human mind and artificial intelligence can approach real-time awareness by reducing perceptual delays. By investigating cosmic signal delay, neurological reaction times, and the ancient cognitive state of stillness, we explore how one may shift from reactive perception to a conscious interface with the near future. This paper introduces both a physical and cognitive model for perceiving the present not as a linear timestamp, but as an interference zone where early-arriving cosmic signals and reactive human delays intersect. We propose experimental approaches to test these ideas using human neural observation and neuro-receptive extensions. Finally, we propose a mathematical framework to guide the evolution of AI systems toward temporally efficient, ethically sound, and internally conscious decision-making processes

The ability to selectively attend to relevant stimuli while filtering out distractions is essential for agents that process complex, high-dimensional sensory input. This paper introduces a model of covert and overt visual attention through the framework of active inference, utilizing dynamic optimization of sensory precisions to minimize free-energy. The model determines visual sensory precisions based on both current environmental beliefs and sensory input, influencing attentional allocation in both covert and overt modalities. To test the effectiveness of the model, we analyze its behavior in the Posner cueing task and a simple target focus task using two-dimensional(2D) visual data. Reaction times are measured to investigate the interplay between exogenous and endogenous attention, as well as valid and invalid cueing. The results show that exogenous and valid cues generally lead to faster reaction times compared to endogenous and invalid cues. Furthermore, the model exhibits behavior similar to inhibition of return, where previously attended locations become suppressed after a specific cue-target onset asynchrony interval. Lastly, we investigate different aspects of overt attention and show that involuntary, reflexive saccades occur faster than intentional ones, but at the expense of adaptability.

Self-supervised learning has become an increasingly important paradigm in the domain of machine intelligence. Furthermore, evidence for self-supervised adaptation, such as contrastive formulations, has emerged in recent computational neuroscience and brain-inspired research. Nevertheless, current work on self-supervised learning relies on biologically implausible credit assignment -- in the form of backpropagation of errors -- and feedforward inference, typically a forward-locked pass. Predictive coding, in its mechanistic form, offers a biologically plausible means to sidestep these backprop-specific limitations. However, unsupervised predictive coding rests on learning a generative model of raw pixel input (akin to ``generative AI'' approaches), which entails predicting a potentially high dimensional input; on the other hand, supervised predictive coding, which learns a mapping between inputs to target labels, requires human annotation, and thus incurs the drawbacks of supervised learning. In this work, we present a scheme for self-supervised learning within a neurobiologically plausible framework that appeals to the free energy principle, constructing a new form of predictive coding that we call meta-representational predictive coding (MPC). MPC sidesteps the need for learning a generative model of sensory input (e.g., pixel-level features) by learning to predict representations of sensory input across parallel streams, resulting in an encoder-only learning and inference scheme. This formulation rests on active inference (in the form of sensory glimpsing) to drive the learning of representations, i.e., the representational dynamics are driven by sequences of decisions made by the model to sample informative portions of its sensorium.

In both neuroscience and artificial intelligence, popular functional frameworks and neural network formulations operate by making use of extrinsic error measurements and global learning algorithms. Through a set of conjectures based on evolutionary insights on the origin of cellular adaptive mechanisms, we reinterpret the core meaning of sensory signals to allow the brain to be interpreted as a negative feedback control system, and show how this could lead to local learning algorithms without the need for global error correction metrics. Thereby, a sufficiently good minima in sensory activity can be the complete reward signal of the network, as well as being both necessary and sufficient for biological learning to arise. We show that this method of learning was likely already present in the earliest unicellular life forms on earth. We show evidence that the same principle holds and scales to multicellular organisms where it in addition can lead to division of labour between cells. Available evidence shows that the evolution of the nervous system likely was an adaptation to more effectively communicate intercellular signals to support such division of labour. We therefore propose that the same learning principle that evolved already in the earliest unicellular life forms, i.e. negative feedback control of externally and internally generated sensor signals, has simply been scaled up to become a fundament of the learning we see in biological brains today. We illustrate diverse biological settings, from the earliest unicellular organisms to humans, where this operational principle appears to be a plausible interpretation of the meaning of sensor signals in biology, and how this relates to current neuroscientific theories and findings.