Efficacy of temporal and spatial abstraction for training accurate machine learning models: A case study in smart thermostats

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.

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

The scientific progress is significantly transforming contemporary society with the introduction and widespread application of technologies like artificial intelligence and quantum computing. Despite their profound impact, these technologies necessitate en ...

Neural networks have shown to be a powerful tool to represent the ground state of quantum many-body systems, including fermionic systems. However, efficiently integrating lattice symmetries into neural representations remains a significant challenge. In th ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

Visual affordance segmentation identifies image regions of an object an agent can interact with. Existing methods re-use and adapt learning-based architectures for semantic segmentation to the affordance segmentation task and evaluate on small-size dataset ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

Federated learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual model updates by nodes also diminishes. In this study, we increase the effe ...

Computing servers have played a key role in developing and processing emerging compute-intensive applications in recent years. Consolidating multiple virtual machines (VMs) inside one server to run various applications introduces severe competence for limi ...

Deriving health indicators of rotating machines is crucial for their maintenance. However, this process is challenging for the prevalent adopted intelligent methods since they may take the whole data distributions, not only introducing noise interference b ...

Machine learning algorithms such as Convolutional Neural Networks (CNNs) are characterized by high robustness towards quantization, supporting small-bitwidth fixed-point arithmetic at inference time with little to no degradation in accuracy. In turn, small ...

Because building-integrated photovoltaic (BIPV) modules are fully integrated into a building envelope, the back of the module can be exposed to little or no ventilation, resulting in increased operating temperatures. As the temperature increases, the perfo ...

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

Training data mixtures greatly impact the generalization performance of large language models. Existing domain reweighting methods often rely on costly weight computations and require retraining when new data is introduced. To this end, we introduce a flex ...

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontriv ...

The aluminium sector relies on natural gas for the conversion of recycled scrap into new feedstock, which results in substantial atmospheric emissions. Hydric resources are also impacted, as they serve as heat sinks for the waste heat generated during the ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

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 ...

Efficacy of temporal and spatial abstraction for training accurate machine learning models: A case study in smart thermostats

Chattez avec Graph Search

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Electrical and Optical Manifestations of Flat Band Physics in Van der Waals Materials

Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations

Meta-learning to address diverse Earth observation problems across resolutions

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

Segmenting Object Affordances: Reproducibility and Sensitivity to Scale

Robust machine learning for neuroscientific inference

Topics in statistical physics of high-dimensional machine learning

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning

CloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds

Classifier-free diffusion-based weakly-supervised approach for health indicator derivation in rotating machines: Advancing early fault detection and condition monitoring

DBFS: Dynamic Bitwidth-Frequency Scaling for Efficient Software-defined SIMD

Correlating long-term performance and aging behaviour of building integrated PV modules

Person Re-Identification and its Application to Multi-Object Tracking

CHAMELEON: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Renewable energy integration and waste heat valorization in aluminum remelting for co-producing kerosene and methanol

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

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