Výsledky vyhledávání

The enormous growth of the complexity of modern computer systems leads to an increasing demand for techniques that support the comprehensibility of systems. This has motivated the very active research field of formal methods that enhance the understa

Externí odkaz: http://arxiv.org/abs/2412.05162

Zobrazit plný text záznamu

Report

Memory-efficient Continual Learning with Neural Collapse Contrastive

Autor: Dang, Trung-Anh, Nguyen, Vincent, Vu, Ngoc-Son, Vrain, Christel

Contrastive learning has significantly improved representation quality, enhancing knowledge transfer across tasks in continual learning (CL). However, catastrophic forgetting remains a key challenge, as contrastive based methods primarily focus on "s

Externí odkaz: http://arxiv.org/abs/2412.02865

Zobrazit plný text záznamu

Report

SNN-Based Online Learning of Concepts and Action Laws in an Open World

Autor: Grimaud, Christel, Longin, Dominique, Herzig, Andreas

We present the architecture of a fully autonomous, bio-inspired cognitive agent built around a spiking neural network (SNN) implementing the agent's semantic memory. The agent explores its universe and learns concepts of objects/situations and of its

Externí odkaz: http://arxiv.org/abs/2411.12308

Zobrazit plný text záznamu

Report

Federated mixed effects logistic regression based on one-time shared summary statistics

Autor: Limpoco, Marie Analiz April, Faes, Christel, Hens, Niel

Upholding data privacy especially in medical research has become tantamount to facing difficulties in accessing individual-level patient data. Estimating mixed effects binary logistic regression models involving data from multiple data providers like

Externí odkaz: http://arxiv.org/abs/2411.04002

Zobrazit plný text záznamu

Report

Evaluating Machine Learning Models against Clinical Protocols for Enhanced Interpretability and Continuity of Care

Autor: Sirocchi, Christel, Suffian, Muhammad, Sabbatini, Federico, Bogliolo, Alessandro, Montagna, Sara

In clinical practice, decision-making relies heavily on established protocols, often formalised as rules. Concurrently, Machine Learning (ML) models, trained on clinical data, aspire to integrate into medical decision-making processes. However, despi

Externí odkaz: http://arxiv.org/abs/2411.03105

Zobrazit plný text záznamu

Report

Hydra-LSTM: A semi-shared Machine Learning architecture for prediction across Watersheds

Autor: Ruparell, Karan, Marks, Robert J., Wood, Andy, Hunt, Kieran M. R., Cloke, Hannah L., Prudhomme, Christel, Pappenberger, Florian, Chantry, Matthew

Long Short Term Memory networks (LSTMs) are used to build single models that predict river discharge across many catchments. These models offer greater accuracy than models trained on each catchment independently if using the same data. However, the

Externí odkaz: http://arxiv.org/abs/2410.16343

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání