Learning continuous-time working memory tasks with on-policy neural reinforcement learning

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

The process of protein aggregation, central to neurodegenerative diseases like Huntington’s, is challenging to study due to its unpredictable nature and relatively rapid kinetics. Understanding its biomechanics is crucial for unraveling its role in disease ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

The mammalian brain develops through precisely orchestrated events that transform a simple neural tube into a complex structure. While single-cell RNA sequencing has revealed remarkable cellular heterogeneity, the lack of spatial context limits our underst ...

Accurate forecasting of photovoltaic (PV) power production is crucial for the integration of more renewable energy sources into the power grid. PV power production is highly intermittent, due to the stochastic cloud behaviour and cloud dynamics. Previous w ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time horizon. Due to the t ...

Accurate segmentation of anatomical substructures within 3D curvilinear structures in medical imaging remains challenging due to their complex geometry and the scarcity of diverse, large-scale datasets for algorithm development and evaluation. In this pape ...

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparen ...

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

Negative symptoms of schizophrenia lack effective treatments. Anomalies in the reward system and cerebellum have been linked to these symptoms. The cerebellum modulates reward circuitry via the ventral tegmental area (VTA). The "cognitive dysmetria theory" ...

A range of behavioral and contextual factors, including eating and drinking behavior, mood, social context, and other daily activities, can significantly impact an individual's quality of life and overall well-being. Therefore, inferring everyday life aspe ...

When a plasma disrupts in a tokamak, significant heat and electromagnetic loads are deposited onto the surrounding device components. These forces scale with plasma current and magnetic field strength, making disruptions one of the key challenges for futur ...

Foundation models have become a powerful tool in single-cell transcriptomics, enabling broad generalization across tasks such as cell type annotation, data integration, and drug response prediction. Yet, most current models are trained predominantly on hea ...

Deep learning models (DLM) are efficient replacements for computationally intensive optimization techniques. Musculoskeletal models (MSM) typically involve resource-intensive optimization processes for determining joint and muscle forces. Consequently, DLM ...

Nuclear Magnetic Resonance (NMR) chemical shifts are powerful probes of local atomic and electronic structure that can be used to resolve the structures of powdered or amorphous molecular solids. Chemical shift driven structure elucidation depends critical ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

Driven by the demand for real-time processing and the need to minimize latency in AI algorithms, edge computing has experienced remarkable progress. Decision-making AI applications stand out for their heavy reliance on data-centric operations, predominantl ...

Learning continuous-time working memory tasks with on-policy neural reinforcement learning

Chattez avec Graph Search

Self-driving microscopy detects the onset of protein aggregation and enables intelligent Brillouin imaging

Robust NAS under adversarial training: benchmark, theory, and beyond

Fine-grained mapping of neural progenitors subtypes in the embryonic brain unveils context-dependent roles of signalling on cell fate decisions

Network time series forecasting in photovoltaics power production

Partial discharge localization in power transformer tanks using machine learning methods

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

A learning-based approach to stochastic optimal control under reach-avoid constraint

Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning

Residual-based attention in physics-informed neural networks

A Longitudinal and Reproducible Anti-coactivation Pattern Between the Cerebellum and the Ventral Tegmental Area Relates to Apathy in Schizophrenia

Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life

Plasma state monitoring and disruption characterization using multimodal VAEs

Abstract IA02: Cancer-specific foundation models: Friend or foe in healthcare AI?

Glenohumeral joint force prediction with deep learning

A Deep Learning Model for Chemical Shieldings in Molecular Organic Solids Including Anisotropy

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

EdgeAI-Aware Design of In-Memory Computing Architectures