惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

宝玉的分享
宝玉的分享
H
Hackread – Cybersecurity News, Data Breaches, AI and More
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
小众软件
小众软件
月光博客
月光博客
D
DataBreaches.Net
L
LangChain Blog
美团技术团队
S
SegmentFault 最新的问题
MyScale Blog
MyScale Blog
大猫的无限游戏
大猫的无限游戏
博客园 - 司徒正美
aimingoo的专栏
aimingoo的专栏
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
H
Help Net Security
阮一峰的网络日志
阮一峰的网络日志
Y
Y Combinator Blog
I
InfoQ
U
Unit 42
Microsoft Azure Blog
Microsoft Azure Blog
J
Java Code Geeks
博客园 - 三生石上(FineUI控件)
腾讯CDC
Martin Fowler
Martin Fowler

cs.NE updates on arXiv.org

MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC Combining Trained Models in Reinforcement Learning Training Non-Differentiable Networks via Optimal Transport ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance Benchmarking local Hebbian learning rules for memory storage and prototype extraction Robust volatility updates for Hierarchical Gaussian Filtering Spiking Sequence Machines and Transformers Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks Attractor FCM Physical Foundation Models: Fixed hardware implementations of large-scale neural networks When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry Learning to Forget: Continual Learning with Adaptive Weight Decay Causal Learning with Neural Assemblies NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning Text-Utilization for Encoder-dominated Speech Recognition Models EdgeSpike: Spiking Neural Networks for Low-Power Autonomous Sensing in Edge IoT Architectures EvoTSC: Evolving Feature Learning Models for Time Series Classification via Genetic Programming Analysis and Explainability of LLMs Via Evolutionary Methods Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs MAEO: Multiobjective Animorphic Ensemble Optimization for Scalable Large-scale Engineering Applications Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks Learn&Drop: Fast Learning of CNNs based on Layer Dropping Architecture-Induced Recoverability Bias in Differentiable Symbolic Regression Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen Structure-Guided Diffusion Model for EEG-Based Visual Cognition Reconstruction
Toward Thermodynamic Reservoir Computing: Exploring SHA-2...
Francisco Angulo de Lafuente, Vladimir Veselov, Richard Goodman · 2026-01-05 · via cs.NE updates on arXiv.org

We propose a theoretical framework--Holographic Reservoir Computing (HRC)--which hypothesizes that the thermodynamic noise and timing dynamics in voltage-stressed Bitcoin mining ASICs (BM1366) could potentially serve as a physical reservoir computing substrate. We present the CHIMERA (Conscious Hybrid Intelligence via Miner-Embedded Resonance Architecture) system architecture, which treats the SHA-256 hashing pipeline not as an entropy source, but as a deterministic diffusion operator whose timing characteristics under controlled voltage and frequency conditions may exhibit computationally useful dynamics. We report preliminary observations of non-Poissonian variability in inter-arrival time statistics during edge-of-stability operation, which we term the "Silicon Heartbeat" hypothesis. Theoretical analysis based on Hierarchical Number System (HNS) representations suggests that such architectures could achieve O(log n) energy scaling compared to traditional von Neumann O(2^n) dependencies. However, we emphasize that these are theoretical projections requiring experimental validation. We present the implemented measurement infrastructure, acknowledge current limitations, and outline the experimental program necessary to confirm or refute these hypotheses. This work contributes to the emerging field of thermodynamic computing by proposing a novel approach to repurposing obsolete cryptographic hardware for neuromorphic applications.