Publications related to Inferring occupant ties: Automated inference of occupant network structure in commercial buildings

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Romain Christophe Rémy Fleury, Janez Rus

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

2024

InterpretCC: Intrinsic User-Centric Interpretability through Global Mixture of Experts

Martin Jaggi, Vinitra Swamy, Jibril Albachir Frej, Julian Thomas Blackwell

Interpretability for neural networks is a trade-off between three key requirements: 1) faithfulness of the explanation (i.e., how perfectly it explains the prediction), 2) understandability of the explanation by humans, and 3) model performance. Most exist ...

2024

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Wenlong Liao, Yi Zhang, Zhe Yang

Recently, remarkable progress has been made in the application of machine learning (ML) techniques (e.g., neural networks) to transformer fault diagnosis. However, the diagnostic processes employed by these techniques often suffer from a lack of interpreta ...

Piscataway2024

Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control

Loris Di Natale

Buildings play a pivotal role in the ongoing worldwide energy transition, accounting for 30% of the global energy consumption. With traditional engineering solutions reaching their limits to tackle such large-scale problems, data-driven methods and Machine ...

EPFL2024

Gibbs sampling the posterior of neural networks

Lenka Zdeborová, Emanuele Troiani, Giovanni Piccioli

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an ...

Bristol2024

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

Paul Scharnhorst

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 ...

EPFL2024

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

Sabine Süsstrunk, Mathieu Salzmann, Tong Zhang, Yi Wu

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 ...

2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Volkan Cevher, Grigorios Chrysos, Fanghui Liu

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

2024

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Spectral Estimators for High-Dimensional Matrix Inference

Farzad Pourkamali

A key challenge across many disciplines is to extract meaningful information from data which is often obscured by noise. These datasets are typically represented as large matrices. Given the current trend of ever-increasing data volumes, with datasets grow ...

EPFL2024

Inferring occupant ties: Automated inference of occupant network structure in commercial buildings

Graph Chatbot

Chat with Graph Search

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

InterpretCC: Intrinsic User-Centric Interpretability through Global Mixture of Experts

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control

Gibbs sampling the posterior of neural networks

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

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

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Spectral Estimators for High-Dimensional Matrix Inference

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

InterpretCC: Intrinsic User-Centric Interpretability through Global Mixture of Experts

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

Spectral Estimators for High-Dimensional Matrix Inference

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control

Gibbs sampling the posterior of neural networks

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

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Deep Learning Theory Through the Lens of Diagonal Linear Networks