This work interprets recurrent and spiking agents as a computational analogue of predictive allostatic organization: distributed control regimes that are predictive, energy-sensitive, action-relevant, and partly causally involved, without claiming biological validation or discrete symbolic categories.
Abstract
Adaptive behavior under partial observability depends on internal organization that carries information beyond the current observation. Drawing on Barrett and Miller's account of categorization as predictive, compressive, functionally organized, and allostatically constrained, we test whether recurrent and spiking agents develop internal states with corresponding computational properties. Agents operate in an energy-constrained foraging task requiring resource acquisition, threat avoidance, contact-dependent consumption, and regulation of an internal energy variable. In a frozen benchmark, learned agents outperform random and heuristic baselines; the trace-augmented recurrent policy is strongest overall, while spiking variants show stress-specific differences. Early internal dynamics predict later full-safe-efficient success above permutation baseline, reaching a maximum ROC-AUC of 0.802. Reduced PCA subspaces retain behaviorally relevant information. Feature-family controls show that predictive signal is distributed across trace, policy-head, internal-dynamics, observation, and allostatic variables, and low-energy state remains strongly decodable after explicit energy-related features are removed. Evaluation-time perturbations to temporal state, sensory information, operating conditions, and allostatic mechanisms alter behavior and/or internal prediction. Seed-balanced event probes show weaker but measurable information about future contact, successful consumption, and threat events, alongside strong low-energy decoding. We interpret this pattern as a computational analogue of predictive allostatic organization: distributed control regimes that are predictive, energy-sensitive, action-relevant, and partly causally involved, without claiming biological validation or discrete symbolic categories.
SpikeWorld, a 1.45M-parameter sparse spiking model jointly trained for heterogeneous sensory prediction, semantics, image-text binding and action-conditioned dynamics, is introduced, showing that the contribution is not superior linear identification, but its integration with a frozen multimodal spiking checkpoint.
This paper evaluates Liquid Neural Networks (LNNs) on an energy-optimal quadrotor control benchmark formulated as a behavioral cloning problem. Several LNN variants, including ordinary differential equation (ODE)-based formulations and closed-form continuous-time (CfC) models, are compared against classical recurrent architectures and a reference multilayer perceptron (MLP). Results show that ODE-based LNNs achieve the strongest closed-loop performance among recurrent models, demonstrating robustness to discretization effects and partial observability while maintaining stable behavior across network sizes. In contrast, CfC variants provide competitive performance under nominal conditions but degrade more significantly under scaling, revealing limitations of its closed-form approximation. While the MLP baseline achieves superior steady-state accuracy and lowest inference latency, it is less reliable under degraded observability and numerical perturbations. Overall, the results emphasize complementary trade-offs between continuous-time recurrent models and feedforward architectures, suggesting that LNNs are particularly well-suited for control tasks involving temporal uncertainty or limited state information.
Tudor M. Avarvarei, Nicolas Drougard, A. Plyer et al.· International Conference on...· 0 citations
Spiking neural networks (SNNs) have garnered significant attention in reinforcement learning tasks for their low power consumption. However, traditional spiking reinforcement learning (SRL) methods, which rely on local-connected encoding and fixed-threshold learning, struggle to capture the inter-dimensional correlations of input information within short timesteps, limiting the network’s expressive capacity at low timesteps. While increasing timesteps can significantly enhance performance, excessive timesteps result in substantial delays. To address this contradiction and enhance the expressive and decision-making capabilities of SNNs within short timesteps, we propose Mask-Adaptive Global Connection (MAGC), a novel encoding method that efficiently captures long-range dependencies via sparse, adaptively masked connections—enabling global feature interaction in a single timestep. Additionally, dynamic-threshold spiking neurons are introduced to effectively capture and distinguish subtle changes in input signals at each timestep, thereby enhancing the spatial-temporal state representation during spike information transmission. Extensive experimental results demonstrate that the proposed method achieves performance comparable to state-of-the-art algorithms using only a single timestep, while significantly reducing inference latency and energy consumption. When extended to multiple timesteps, our approach consistently outperforms existing methods, showing substantial improvements across eight continuous control tasks from OpenAI Gym.
Rong Xiao, Zhiyuan Hu, Ping He et al.· IEEE Transactions on Image P...· 0 citations
Training RNNs on delayed decision-making tasks with progressively increasing temporal demands shows that temporal and decision-related computations can emerge through multiple dynamical regimes, while maintaining structured low-dimensional representations and comparable behavioural performance, mirroring biological principles of degeneracy and functional redundancy.
Cecilia Jarne, Ryeongkyung Yoon, Tahra L. Eissa et al.· Journal of Computational Neu...· 0 citations
This analysis explains why conditional mutual information alone cannot certify escape and measures variation among intervention-conditioned updates rather than departure from the no-intervention law.
Liquid State Machines (LSM) are spiking recurrent neural networks inspired by the dynamics of the human brain. By encoding information as discrete spikes, they enable low-power and real-time data processing at the edge. Despite the benefits of this computational model, the design of efficient LSM still lacks a widely accepted methodological foundation. Existing approaches often rely on arbitrary parameter tuning and large reservoir sizes, which are computationally costly and demand prior domain-specific knowledge. In this work, we introduce a systematic methodology for simplifying LSM design while substantially reducing the number of required neurons and synapses. This significantly reduces power consumption, bringing this class of models closer to their original motivation of ultra-low-power processing directly at the sensor level. A hybrid metaheuristic combining hill climbing and genetic programming (HC-GP) optimizes the LSM design, guiding the network to efficiently capture input patterns while avoiding random connectivity inefficiencies. Experimental results on the N-TIDIGITS and FSDD benchmarks demonstrate the effectiveness of the approach, achieving 82.3% accuracy on N-TIDIGITS, significantly surpassing existing models of comparable size, and 92.7% on FSDD, achieving state-of-the-art accuracy with only 66 neurons (6.6% of the neurons reported in previous state-of-the-art networks).
Andrés Romo, Andrés Otero, J. M. Lanza-Gutiérrez· Annual Conference on Genetic...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
