arXiv:2603.21918v1 Announce Type: new Abstract: This paper develops a unified framework for measuring concentration in weighted systems embedded in networks of interactions. While traditional indices such as the Herfindahl-Hirschman Index capture dispersion in weights, they neglect the topology of relationships among the elements receiving those weights. To address this limitation, we introduce a family of topology-aware concentration indices that jointly account for weight distributions and network structure. At the core of the framework lies a baseline Network Concentration […]

Ver mais

Preliminaries Committee Boosting The committee has an equal weight for every prediction from all models, and it gives little improvement than a single model. Then boosting was built for this problem. Boosting is a technique of combining multiple ‘base’ classifiers to produce a form of the committee that: performances better than any of the base classifiers and each base classifier has a different weight factor Adaboost Adaboost is short for adaptive boosting.

Ver mais

Code is finally public. Some of you asked for it after my earlier posts. github.com/MarcHesse/mhflocke What it is: 4,650 Izhikevich spiking neurons with R-STDP (reward-modulated spike-timing-dependent plasticity) Central Pattern Generator for innate gait Cerebellar forward model (Marr-Albus-Ito) for balance correction Competence gate: CPG fades as the SNN proves it can walk Results (Unitree Go2, MuJoCo, 10 seeds, 50k steps): Full system: 45.15 ± 0.67m PPO baseline: 12.83 ± 7.78m Zero falls GitHub: github.com/MarcHesse/mhflocke Paper: doi.org/10.5281/zenodo.19336894 Paper: aixiv.science/abs/aixiv.260301.000002 Docs: […]

Ver mais

arXiv:2604.04673v1 Announce Type: cross Abstract: Bayesian neural networks (BNNs) offer a natural probabilistic formulation for inference in deep learning models. Despite their popularity, their optimality has received limited attention through the lens of statistical decision theory. In this paper, we study decision rules induced by deep, fully connected feedforward ReLU BNNs in the normal location model under quadratic loss. We show that, for fixed prior scales, the induced Bayes decision rule is not minimax. We then propose a […]

Ver mais

The dataset distributions in offline reinforcement learning (RL) often exhibit complex and multi-modal distributions, necessitating expressive policies to capture such distributions beyond widely-used Gaussian policies. To handle such complex and multi-modal datasets, in this paper, we propose Flow Actor-Critic, a new actor-critic method for offline RL, based on recent flow policies. The proposed method not only uses the flow model for actor as in previous flow policies but also exploits the expressive flow model for conservative critic acquisition […]

Ver mais

Survival analysis is essential for clinical decision-making, as it allows practitioners to estimate time-to-event outcomes, stratify patient risk profiles, and guide treatment planning. Deep learning has revolutionized this field with unprecedented predictive capabilities but faces a fundamental trade-off between performance and interpretability. While neural networks achieve high accuracy, their black-box nature limits clinical adoption. Conversely, deep clustering-based methods that stratify patients into interpretable risk groups typically sacrifice predictive power. We propose CONVERSE (CONtrastive Variational Ensemble for Risk Stratification […]

Ver mais

Quadruped locomotion provides a natural setting for understanding when model-free learning can outperform model-based control design, by exploiting data patterns to bypass the difficulty of optimizing over discrete contacts and the combinatorial explosion of mode changes. We give a principled analysis of why imitation learning with quadrupeds can be inherently effective in a small data regime, based on the structure of its limit cycles, Poincaré return maps, and local numerical properties of neural networks. The understanding motivates a […]

Ver mais

Google’s Nano Banana Pro is a game-changer in light image generation, particularly for marketers and storytellers who need speed and highly contextual image generation. The location-aware visual content that depicts the place, the surroundings, and the cultural signs is going to be one of the strongest points in AI storytelling tools. This is where the Nano Banana image model gets its edge. It combines intelligent imaging with good architecture and gives the creator the power to create visuals […]

Ver mais

arXiv:2603.12305v1 Announce Type: new Abstract: The ability to understand and reason about cause and effect — encompassing interventions, counterfactuals, and underlying mechanisms — is a cornerstone of robust artificial intelligence. While deep learning excels at pattern recognition, it fundamentally lacks a model of causality, making systems brittle under distribution shifts and unable to answer “what-if” questions. This paper introduces the emph{Hierarchical Causal Primitive Dynamic Composition Network (HCP-DCNet)}, a unified framework that bridges continuous physical dynamics with discrete symbolic […]

Ver mais