Data & Analytics

Unified Rosetta Stone framework for neural mass models. Provides mathematical tools connecting different neural mass model formulations for brain dynamics analysis across scales from single-neuron spiking to macroscopic fMRI/MEG/EEG. Applies to: brain dynamics modeling, neural mass models, computational neuroscience, multi-scale brain modeling. Activation: neural mass models, rosetta stone neural, brain dynamics tools, neural mass unified, computational brain modeling.

Neural manifold learning dynamics methodology for analyzing population activity in high-dimensional neural state spaces. Extracts low-dimensional structure from neural recordings to understand computation and behavior. Activation triggers: neural manifold, latent dynamics, population activity, dimensionality reduction, neural state space, behavior decoding.

Deep learning-based decoders for quantum error correction (QEC) that outperform traditional algorithms (MWPM, belief propagation) in speed and adaptability to realistic noise models.

Theory of critical dynamics and information processing in neural networks. Neural systems at critical points exhibit optimal information processing, maximal dynamic range, and power-law distributed avalanches. Provides methods for identifying, analyzing, and exploiting critical regimes in both biological and artificial neural networks. Applicable to critical brain hypothesis, neural avalanche analysis, optimal computation regimes. Trigger: neural criticality, critical dynamics, neural avalanc...

脑连接矩阵交互式可视化工具。基于HTML5/JavaScript的浏览器端应用，支持EEG、ECoG、MEG、fMRI等高维神经连接数据的3D堆叠矩阵可视化，实时交互探索连接模式。适用于脑连接分析、神经数据可视化、连接组学。触发词：脑连接可视化、连接矩阵、神经网络可视化、connectivity matrix、brain connectivity visualization、EEG connectivity、MEG connectivity。

神经编码动力学分析框架 - 整合计算神经科学、机器学习和临界态理论，研究生物与人工神经网络编码表示动力学。涵盖临界脑假说、雪崩动力学、信息几何与动力学不变量。Activation: neural coding, dynamics analysis, critical brain hypothesis, avalanche dynamics, information geometry, dynamical invariants, neural representation, encoding dynamics, computational neuroscience.

Multi-view Information Bottleneck framework for modeling higher-order interactions (HOIs) in resting-state fMRI for psychiatric diagnosis. Captures complex brain dynamics beyond pairwise connectivity without predefined hyperedges.

Multisensory learning methodology that recruits visual neurons into olfactory memory engrams through cross-modal binding. Using Drosophila model to study how combining sensory modalities expands memory engrams and improves recall performance. Activation triggers: multisensory learning, memory engram, cross-modal binding, neural circuits, sensory integration.

Multi-view O-Information framework for modeling higher-order brain interactions (HOIs) in fMRI data. Information-theoretic approach to psychiatric diagnosis using triadic and tetradic brain connectivity patterns. Keywords: O-information, higher-order interactions, fMRI analysis, information bottleneck, psychiatric diagnosis, hypergraph

Multi-Source Multi-View Graph Domain Adaptation with Hyperbolic Residual Encoding framework for cross-site Major Depressive Disorder (MDD) identification from resting-state fMRI. Use when working with multi-site neuroimaging data, cross-domain brain network analysis, heterogeneous functional connectivity views, or hyperbolic representation learning for clinical applications.

Multi-scale information geometry framework revealing the structure of mutual information in neural populations. A unique Riemannian representational geometry emerges from coarse-graining, extending Fisher information metric to capture encoding structure from fine to coarse stimulus distinctions. Use when researching neural population coding, information geometry, Fisher information in neuroscience, or neural representational geometry. Based on arXiv:2605.06304.

Derived from arXiv:2607.17044 - Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent

**arXiv ID:** 2304.12180 **Authors:** Oscar Li, James Harrison, Jascha Sohl-Dickstein, Virginia Smith, Luke Metz **Published:** 2023-04-21T17:53:05Z **Abstract:** Unrolled computation graphs are prevalent throughout machine learning but present challenges to automatic differentiation (AD) gradient estimation methods when their loss functions exhibit extreme local sensitivtiy, discontinuity, or blackbox characteristics. In such scenarios, online evolution strategies methods are a more capable ...

Skill derived from arXiv:2607.17948 - Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking

**arXiv ID:** 1811.08225 **Authors:** Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata **Published:** 2018-11-20T13:00:51Z **Abstract:** Learning classifier systems (LCSs) are evolutionary machine learning algorithms, flexible enough to be applied to reinforcement, supervised and unsupervised learning problems with good performance. Recently, self organizing classifiers were proposed which are similar to LCSs but have the advantage that in its structured population no balance betwe...

**arXiv ID:** 2603.06142 **Authors:** Björn van Zwol **Published:** 2026-03-06T10:50:41Z **Abstract:** Predictive coding graphs (PCGs) are a recently introduced generalization to predictive coding networks, a neuroscience-inspired probabilistic latent variable model. Here, we prove how PCGs define a mathematical superset of feedforward artificial neural networks (multilayer perceptrons). This positions PCNs more strongly within contemporary machine learning (ML), and reinforces earlier propos...

**arXiv ID:** 1908.06040 **Authors:** Felipe Moreno-Vera **Published:** 2019-08-16T15:56:16Z **Abstract:** Currently, many applications in Machine Learning are based on define new models to extract more information about data, In this case Deep Reinforcement Learning with the most common application in video games like Atari, Mario, and others causes an impact in how to computers can learning by himself with only information called rewards obtained from any action. There is a lot of algorithm...

**arXiv ID:** 2207.08389 **Authors:** Amir H. Ashouri, Mostafa Elhoushi, Yuzhe Hua, Xiang Wang, Muhammad Asif Manzoor, Bryan Chan, Yaoqing Gao **Published:** 2022-07-18T05:47:29Z **Abstract:** For the past 25 years, we have witnessed an extensive application of Machine Learning to the Compiler space; the selection and the phase-ordering problem. However, limited works have been upstreamed into the state-of-the-art compilers, i.e., LLVM, to seamlessly integrate the former into the optimization...

**arXiv ID:** 1806.07917 **Authors:** Chrisantha Thomas Fernando, Jakub Sygnowski, Simon Osindero, Jane Wang, Tom Schaul, Denis Teplyashin, Pablo Sprechmann, Alexander Pritzel, Andrei A. Rusu **Published:** 2018-06-06T08:39:03Z **Abstract:** The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan. To this date there has been no demonstration of its necessity in empirically challenging tasks. Here we show that ...

**arXiv ID:** 2503.03084 **Authors:** Ashwin Viswanathan Kannan, Johnson P Thomas, Abhimanyu Mukerji **Published:** 2025-03-05T00:53:22Z **Abstract:** The exponential rise in data generation has led to vast, heterogeneous datasets crucial for predictive analytics and decision-making. Ensuring data quality and semantic integrity remains a challenge. This paper presents a brain-inspired distributed cognitive framework that integrates deep learning with Hopfield networks to identify and link sem...

Regime-based portfolio allocation integrating Hidden Markov Models with Reinforcement Learning. Three-state HMM detects market regimes, RL enhances allocation. Outperforms SPY benchmark with lower drawdowns. arXiv:2605.27848

Autonomous emergence of Hamiltonian parameters in deep generative models via Riemannian diffusion score fields. Extracting implicit physical laws from trained neural networks using algebraic framework. Activation: Hamiltonian, deep generative model, Riemannian diffusion, score field, spin glass, equivariant attention, physical law discovery, force estimator, emergent physics.

**arXiv ID:** 2202.00155 **Authors:** Hattie Zhou, Ankit Vani, Hugo Larochelle, Aaron Courville **Published:** 2022-02-01T00:15:58Z **Abstract:** Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact be favorable to learning. We introduce "forget-and-relearn" as a powerful paradigm for shaping the learning trajectories of artificial neural networks. In this process, the forgetting step selectively removes und...

**arXiv ID:** 2004.12846 **Authors:** Eseoghene Ben-Iwhiwhu, Pawel Ladosz, Jeffery Dick, Wen-Hua Chen, Praveen Pilly, Andrea Soltoggio **Published:** 2020-04-27T14:55:08Z **Abstract:** Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning. However, reinforcement learning (RL) algorithms struggle in POMDP environments because the state of the system, essential in a RL framework, is not always visible. Additio...