Data & Analytics

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...

**arXiv ID:** 2106.06061 **Authors:** Daniel J. B. Harrold, Jun Cao, Zhong Fan **Published:** 2021-06-10T21:27:35Z **Abstract:** As the world seeks to become more sustainable, intelligent solutions are needed to increase the penetration of renewable energy. In this paper, the model-free deep reinforcement learning algorithm Rainbow Deep Q-Networks is used to control a battery in a small microgrid to perform energy arbitrage and more efficiently utilise solar and wind energy sources. The grid ...

**arXiv ID:** 2608.26086v1 **Authors:** Jiarui Yan, Weiwei Sun, Sijie Li, Wenhan Li, Yiming Yang **URL:** http://arxiv.org/abs/2608.26086v1 **Utility Score:** 1.00

**arXiv ID:** 2004.07707 **Authors:** Declan Oller, Tobias Glasmachers, Giuseppe Cuccu **Published:** 2020-04-16T15:32:52Z **Abstract:** We propose a novel method for analyzing and visualizing the complexity of standard reinforcement learning (RL) benchmarks based on score distributions. A large number of policy networks are generated by randomly guessing their parameters, and then evaluated on the benchmark task; the study of their aggregated results provide insights into the benchmark compl...

MLE-Toolbox: Comprehensive open-source MATLAB toolbox for end-to-end EEG/MEG analysis with source localization, connectivity analysis, and ML classifiers. Activation: MLE-Toolbox, EEG analysis, MEG analysis, source localization, brain network analysis, neuroimaging toolbox.

Maximum Likelihood Decoding methodology for CSS quantum error correction codes — reformulates MLD as partition function computation in classical spin models, enabling exact MLD via tensor network contraction and approximate MLD via belief propagation. Connects QEC threshold to statistical phase transition. Use when: designing quantum error correction decoders, analyzing CSS code thresholds, computing MLD for surface/toric codes, applying tensor networks to QEC, or studying statistical mechani...

Machine Learning Methods for Studying Latent Neural Activity Dynamics - IJCAI 2026 survey综述机器学习研究神经种群潜伏动力学结构的方法论，涵盖单区域潜伏动力学（LDS/RNN/Neural ODE）、多区域通信、行为对齐建模、神经基础模型（Transformer/扩散模型）

ML-hybrid distributed caching methodology combining traditional caching algorithms (LRU, LFU, ARC, TLRU) with lightweight machine learning for predictive eviction and adaptive sizing. Use when: (1) designing cache systems for dynamic environments, (2) selecting caching strategy based on workload characteristics, (3) implementing ML-enhanced eviction/prefetching layers, (4) optimizing cache performance across distributed architectures, (5) benchmarking caching algorithms across hit ratio, late...

Computational complexity lens for understanding how ML manages complex systems. Based on arxiv:2604.07233 'How Does Machine Learning Manage Complexity?' by Lance Fortnow. Use when analyzing ML's ability to model complex systems, understanding complexity bounds, P/poly-computable distributions, or when asked 'how does ML handle complexity?', 'ML complexity theory', 'computable distributions in ML'.

MIRAGE methodology — robust multi-modal architecture for translating fMRI-to-image models from seen visual decoding to mental imagery reconstruction. Demonstrates that SOTA on seen images doesn't guarantee SOTA on mental imagery and proposes a multi-modal, multi-loss architecture that excels at both. Use when researching: fMRI visual decoding, mental imagery reconstruction, brain decoding generalization, seen-to-imagery transfer, NSD-Imagery dataset, multi-modal brain decoding, vision model g...

Energy-first neural architecture design framework based on biological principles. Systematic validation across vision, text, neuromorphic, and physiological datasets with 2,203 experiments. Activation: energy-first, neural architecture, biological principles, energy-regularized, lambda sweep.

元学习上下文方法实现无需训练的跨被试脑解码。通过上下文学习实现训练无关的跨个体fMRI解码。适用于零样本脑解码、快速脑机接口、个体化神经科学。触发词：元学习脑解码、上下文学习、跨被试、训练无关、零样本。

Meta-Learning Biologically Plausible Plasticity Rules

Measurement-based soft PCA framework using entropy-regularized Fermi-Dirac filters for quantum principal component analysis without eigenvector recovery. Enables dimension-independent sample complexity O(1/eta^2) for fractional-rank scoring. Use when: quantum PCA, soft PCA, Fermi-Dirac filter, measurement-based PCA, quantum data analysis, eigenvector-free PCA, anomaly detection via PCA, spectral energy profiling.

Dynamical mean-field theory for random recurrent networks with low-rank structure and firing-rate-driven adaptation. Identifies four oscillatory regimes: static coherent, noise-sustained oscillations, stochastic switching, global limit cycle. Explains waxing-waning rhythms, Up-Down alternations observed in wakefulness/sleep/anesthesia. Trigger words: mean-field theory, oscillatory dynamics, low-rank recurrent network, Hopf bifurcation, adaptation, neural oscillations, Up-Down states.

Monte Carlo Tree Search (MCTS) methodology for discovering optimal data encoding circuits in quantum-classical neural networks. Addresses the open question of why certain quantum data encodings outperform others by treating encoding circuit design as a sequential decision problem. Use when: quantum data encoding optimization, MCTS quantum circuits, quantum-classical neural network design, QML encoding strategy, quantum feature map discovery.

Multilevel Covariate-Assisted Principal Regression (MCAP) for brain functional connectivity analysis. Handles hierarchically nested neuroimaging data, identifies cluster-specific projections, and models covariance matrix outcomes with subject-level covariates. Use when: analyzing lifespan brain connectivity, multilevel fMRI data, functional connectivity regression, covariance matrix outcomes.

Maximum entropy principle for neural network connectivity — normative framework for understanding how task constraints shape neural connectivity structure without gradient descent.

Tensor network diagram methodology for simplifying tensor algebra - graphical notation for contractions, decompositions, and gradient computation bridging quantum physics notation with machine learning. Activation: tensor network diagrams, tensor cookbook, penrose notation, tensor contraction diagrams, 张量网络图, 张量图解.

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.

Geometric analysis of attractor boundaries and storage capacity limits in kernel Hopfield networks trained with Kernel Logistic Regression (KLR). Covers attractor basin geometry, Ridge of Optimization, morphing analysis, SNR vs Cover's theorem, and dynamical stability. Activation: kernel Hopfield, KLR associative memory, attractor basin geometry, Ridge of Optimization, morphing analysis Hopfield, storage capacity Hopfield, SNR analysis Hopfield, Cover's theorem associative memory, crosstalk n...

Bayesian decision-making framework for membership inference attacks on statistical releases using Bayesian network population models. Reframes membership inference with respect to populations represented as Bayesian networks, enabling more effective specialized attacks by incorporating prior information about attribute dependency structures. Use when analyzing statistical disclosure risk, designing membership inference attacks, or evaluating privacy of released statistics.