Customized Neural Network training to predict the highly imbalanced data of domestic hot water usage

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

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 ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

The recent geopolitical conflicts in Europe have underscored the vulnerability of the current energy system to the volatility of energy carrier prices. In the prospect of defining robust energy systems ensuring sustainable energy supply in the future, the ...

Water vitrifies if cooled at rates above 3 × 105 K/s. In contrast, when the resulting amorphous ice is flash heated, crystallization occurs even at a more than 10 times higher heating rate, as we have recently shown. This may present an issue for microseco ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Water can be vitrified if it is cooled at high rates, which makes it possible to outrun crystallization in so-called no man’s land, a range of deeply supercooled temperatures where water crystallizes rapidly. Here, we study the reverse process in pure wate ...

In this work, a tool to design district heating networks (DHN) is presented and applied to the city of Lausanne as a case study. The evaluation of the buildings’ heat/cooling demand is performed using a Geographic Information System (GIS) database, built f ...

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 ...

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 ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

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 ...

Magnonics is a research field that has gained an increasing interest in both the fundamental and applied sciences in recent years. This field aims to explore and functionalize collective spin excitations in magnetically ordered materials for modern informa ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

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 ...

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 ...

The reported rate of the occurrence of unilateral spatial neglect (USN) is highly variable likely due to the lack of validity and low sensitivity of classical tools used to assess it. Virtual reality (VR) assessments try to overcome these limitations by pr ...

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Customized Neural Network training to predict the highly imbalanced data of domestic hot water usage

Chat with Graph Search

Gibbs sampling the posterior of neural networks

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Identification of typical district configurations: A two-step global sensitivity analysis framework

Shaped Laser Pulses for Microsecond Time-Resolved Cryo-EM: Outrunning Crystallization during Flash Melting

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Flash Melting Amorphous Ice

Decomposition method to evaluate district heating/cooling network potential at urban scale

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Topics in statistical physics of high-dimensional machine learning

Sparse autoregressive neural networks for classical spin systems

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Random matrix methods for high-dimensional machine learning models

Machine Learning for Modeling Stock Returns

Deep Learning Theory Through the Lens of Diagonal Linear Networks

The 2024 Magnonics Roadmap

Safe Deep Neural Networks

Robust machine learning for neuroscientific inference

Generalization of Scaled Deep ResNets in the Mean-Field Regime

An immersive virtual reality tool for assessing left and right unilateral spatial neglect

On the Generalization of Stochastic Gradient Descent with Momentum