Data & Analytics

Comprehensive review of nonequilibrium physics in neuroscience. Analyzes time-irreversibility, entropy production, and broken detailed balance in neural dynamics as signatures of cognitive complexity and consciousness.

Information geometry framework for analyzing non-Euclidean structure of visual space — modeling perceptual geometry using Riemannian manifolds, Fisher information, and Finsler geometry. Activation: visual space, non-Euclidean, information geometry, Riemannian manifold, perceptual geometry, Fisher information, visual perception, psychophysics.

Noise-enhanced quantum kernel methods for analog quantum computing. Implements analog and hybrid quantum kernels with noise-induced performance improvements for quantum machine learning. Activation: noise quantum kernel, analog quantum kernel, quantum kernel noise

Neural network encoding methodology for quantum state preparation: trains classical neural network to map input data directly to quantum circuit parameters, avoiding per-instance variational optimization. Achieves 0.992 fidelity on unseen data with 5000x runtime reduction. Use when designing QML data loading pipelines, quantum state preparation, neural-encoded quantum circuits, or amplitude encoding optimization.

Zero-shot imagined speech decoding from MEG via imagined-to-listened cross-condition mapping. Trains models to map imagined MEG responses to listened responses, then decodes using listened-only decoder. Three-stage pipeline: (1) mapping imagined→listened MEG, (2) train contrastive word decoder on listened MEG with multi-embedding evaluation, (3) decode imagined speech via mapping pipeline on held-out subjects. Use when: imagined speech decoding, MEG BCI, cross-condition neural mapping, zero-s...

Transformer 表征轨迹几何分析方法论 - 将计算神经科学的几何工具应用于 Transformer 可解释性研究，无需探测即可分析表征动力学

**arXiv ID:** 2302.06675 **Authors:** Xiangning Chen, Chen Liang, Da Huang, Esteban Real, Kaiyuan Wang, Yao Liu, Hieu Pham, Xuanyi Dong, Thang Luong, Cho-Jui Hsieh, Yifeng Lu, Quoc V. Le **Published:** 2023-02-13T20:27:30Z **Abstract:** We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient search techniques to explore an infinite and sparse program space. To bridge the la...

Renormalization Group (RG) interpretability framework for deep neural networks. Establishes correspondence between RG in statistical physics and DNN training, proving DNN feature extraction is equivalent to RG flow on exponential family distributions. Based on arXiv:2606.00157 (Gong & Xia, 2026).

利用大型语言模型进行神经信号解码的前沿方法。实现从脑活动到自然语言的直接转换，支持脑-文本接口。

This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks. While traditional expl. Based on arXiv:2607.07316.

Conserved Kinematic Representations for Zero-Shot Decoding in Handwriting BCIs. Methodology aligning neural activity to imagined kinematics for zero-shot capable ML decoding of unseen characters in BCI systems. Use when: researching brain-computer interfaces, motor cortex representations, zero-shot decoding, handwriting BCIs, kinematic primitives, logographic language neuroprosthetics, compositional motor control. Keywords: zero-shot BCI, kinematic representation, handwriting decoding, motor ...

**arXiv ID:** 2302.14051 **Authors:** Alexander C. Li, Ellis Brown, Alexei A. Efros, Deepak Pathak **Published:** 2023-02-27T18:59:55Z **Abstract:** Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets. These general-purpose models only capture the knowledge within their pre-training datasets, which are tiny, out-of-date snapshots of the Internet -- where billions of images are uploaded each day. We suggest an alternate approach: rath...

**arXiv ID:** 2305.10449 **Authors:** Ahsan Adeel, Junaid Muzaffar, Fahad Zia, Khubaib Ahmed, Mohsin Raza, Eamin Chaudary, Talha Bin Riaz, Ahmed Saeed **Published:** 2023-05-16T16:48:12Z **Abstract:** Going beyond 'dendritic democracy', we introduce a 'democracy of local processors', termed Cooperator. Here we compare their capabilities when used in permutation invariant neural networks for reinforcement learning (RL), with machine learning algorithms based on Transformers, such as ChatGPT. T...

Brain-LLM alignment is driven by training-language dominance, not an inherent property of English. Tests with fMRI from 112 participants across English, Chinese, French and 7 LLMs (English-dominant, Chinese-dominant, multilingual). Baichuan2-7B reverses alignment gradient entirely; typological distance independently affects alignment degradation in syntax regions (IFG). Accepted at CoNLL 2026. Activation: brain-LLM alignment, cross-linguistic brain encoding, training data dominance, multiling...

... Activation: fMRI, functional MRI, brain imaging, brain network, graph, connectivity

**arXiv ID:** 1707.00703 **Authors:** Emmanuel Dufourq, Bruce A. Bassett **Published:** 2017-07-03T18:00:08Z **Abstract:** Regression or classification? This is perhaps the most basic question faced when tackling a new supervised learning problem. We present an Evolutionary Deep Learning (EDL) algorithm that automatically solves this by identifying the question type with high accuracy, along with a proposed deep architecture. Typically, a significant amount of human insight and preparation is...

**arXiv ID:** 2302.04181 **Authors:** Luis Müller, Mikhail Galkin, Christopher Morris, Ladislav Rampášek **Published:** 2023-02-08T16:40:11Z **Abstract:** Recently, transformer architectures for graphs emerged as an alternative to established techniques for machine learning with graphs, such as (message-passing) graph neural networks. So far, they have shown promising empirical results, e.g., on molecular prediction datasets, often attributed to their ability to circumvent graph neural networ...

**arXiv ID:** 1908.04784 **Authors:** Jordan J. Bird, Diego R. Faria, Luis J. Manso, Anikó Ekárt, Christopher D. Buckingham **Published:** 2019-08-13T16:49:30Z **Abstract:** This study suggests a new approach to EEG data classification by exploring the idea of using evolutionary computation to both select useful discriminative EEG features and optimise the topology of Artificial Neural Networks. An evolutionary algorithm is applied to select the most informative features from an initial set o...

NeuroSTORM - Neuroimaging Foundation Model with Spatial-Temporal Optimized Representation for fMRI analysis. Trained on 28.65M frames from 50,000 subjects using shifted scanning Mamba backbone. Activation triggers: fMRI foundation model, neuroimaging, NeuroSTORM, brain analysis, Mamba fMRI, spatial-temporal modeling.

Zero-shot imagined speech decoding from MEG via imagined-to-listened cross-condition mapping. Trains models to map imagined MEG responses to listened responses, then decodes using listened-only decoder. Three-stage pipeline: (1) mapping imagined→listened MEG, (2) train contrastive word decoder on listened MEG with multi-embedding evaluation, (3) decode imagined speech via mapping pipeline on held-out subjects. Use when: imagined speech decoding, MEG BCI, cross-condition neural mapping, zero-s...

YANA: Bridging the Neuromorphic Simulation-to-Hardware Gap. Framework for seamless translation of SNN algorithms from simulation to neuromorphic hardware deployment. Activation: YANA, simulation-to-hardware, neuromorphic deployment, SNN hardware gap.

Wavelet Scattering Transform (WST) framework for interpretable schizophrenia biomarker discovery and classification from resting-state EEG. Multi-order scattering coefficients capture cross-frequency coupling and amplitude modulation dynamics, achieving 90.48% accuracy under strict subject-independent evaluation.

Multi-Stage Warm-Start (MSWS) deep learning framework for Unit Commitment optimization. Combines neural network warm-starting with MILP constraints to accelerate power grid scheduling. Use for unit commitment, power system optimization, energy scheduling, and MILP warm-starting.

--- name: visual-cortex-diffusion-model description: "Skill for understanding and applying the mechanistic model of inference in visual cortex equivalent to a minimal diffusion model, linking sparse coding with recurrent dynamics and horizontal connections in V1. Based on arXiv:2607.15693." activation: visual cortex diffusion model, sparse coding inference, recurrent diffusion model