Statistical mechanics of deep learning

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.

Demographic fairness or equity is a crucial aspect of machine learning models, particularly in critical domains such as healthcare, where errors can have severe consequences. A fair model avoids making distinctions between groups with different sensitive o ...

Laser material processing (LMP) has revolutionized modern manufacturing, emerging as a cornerstone technology valued for its precision, speed, and versatility, especially in high-stakes sectors like aerospace, automotive, and medical device production. Des ...

We study the random binary symmetric perceptron problem, focusing on the behavior of rare high-margin solutions. While most solutions are isolated, we demonstrate that these rare solutions are part of clusters of extensive entropy, heuristically correspond ...

Our understanding of the generalization capabilities of neural networks (NNs) is still incomplete. Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from gradient-free metho ...

The sum-of-squares (SOS) approximation method is a technique used in optimization problems to derive lower bounds on the optimal value of an objective function. By representing the objective function as a sum of squares in a feature space, the SOS method t ...

We establish shape holomorphy results for general weakly- and hyper-singular boundary integral operators arising from second-order partial differential equations in unbounded two-dimensional domains with multiple finite-length open arcs. After recasting th ...

A novel technique based on machine learning is introduced to reconstruct the decays of highly Lorentz boosted particles. Using an end-to-end deep learning strategy, the technique bypasses existing rule-based particle reconstruction methods typically used i ...

Supplementary files containing datasets needed to reproduce the results of the manuscript "Generative machine learning produces kinetic models that accurately characterize intracellular metabolic states" by S. Choudhury et al. The code to use with these da ...

Data redundancy has been one of the most important problems in data-intensive applications such as data mining and machine learning. Removing data redundancy brings many benefits in efficient data updating, effective data storage, and error-free query proc ...

In medical image segmentation, supervised deep networks' success comes at the cost of requiring abundant labeled data. While asking domain experts to annotate only one or a few of the cohort's images is feasible, annotating all available images is impracti ...

Despite the high number of investments for data-based models in the expansion of Industry 4.0, too little effort has been made to ensure the maintenance of those models. In a data-streaming environment, data-based models are subject to concept drifts. A co ...

Effective caching is crucial for performance of modern-day computing systems. A key optimization problem arising in caching – which item to evict to make room for a new item – cannot be optimally solved without knowing the future. There are many classical ...

This thesis aims to explore and exploit trade-offs in integrated circuits and systems to overcome the fundamental bottlenecks faced by future data acquisition and communication systems. Specifically, we target the emerging implantable neurotechnology and t ...

Superagers are defined as older adults who have youthful memory performance comparable to that of middle-aged adults. Classifying superagers based on the brain connectome using machine learning modeling can provide important insights on the physiology unde ...

Using Machine Learning (ML) algorithms for classification of the existing residential neighbourhoods and their spatial characteristics (e.g. density) so as to provide plausible scenarios for designing future sustainable housing is a novel application. Here ...

Removal of noise from fluorescence microscopy images is an important first step in many biological analysis pipelines. Current state-of-the-art supervised methods employ convolutional neural networks that are trained with clean (ground-truth) images. Recen ...

Changes in stem cell activity may underpin aging. However, these changes are not completely understood. Here, we combined single-cell profiling with machine learning and in vivo functional studies to explore how hematopoietic stem cell (HSC) divisions patt ...

Modern machine learning methods and their applications in computer vision are known to crave for large amounts of training data to reach their full potential. Because training data is mostly obtained through humans who manually label samples, it induces a ...

For an autonomous car, getting surprised is the worst thing that can happen. To prevent that, plenty of studies are trying to forecast traffic participants’ actions especially in an urban scene using recurrent networks. Recurrent networks are used for temp ...

Statistical mechanics of deep learning

Chat with Graph Search

Optimizing fairness and utility in healthcare machine learning models

Toward Autonomous Laser Manufacturing: Solving Key Challenges in Optimization, Monitoring, and Control

On the atypical solutions of the symmetric binary perceptron

Neural Redshift: Random Networks are not Random Functions

Theory and applications of the sum-of-squares technique

Shape Holomorphy of Boundary Integral Operators on Multiple Open Arcs

Reconstruction of decays to merged photons using end-to-end deep learning with domain continuation in the CMS detector

Supplementary datasets for the manuscript "Generative machine learning produces kinetic models that accurately characterize intracellular metabolic states" -Part 2

Validating functional redundancy with mixed generative adversarial networks

Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation

Data-based model maintenance in the era of industry 4.0: A methodology

Robust Learning-Augmented Caching: An Experimental Study

Resource Trade-Offs in Circuits and Systems: from Neurotechnology to Communications

Predicting Superagers by Machine Learning Classification Based on the Functional Brain Connectome Using Resting-State Functional Magnetic Resonance Imaging

Beam Measurements and Machine Learning at the CERN Large Hadron Collider

Residential density classification for sustainable housing development using a machine learning approach

Removing Structured Noise With Self-Supervised Blind-Spot Networks

Machine Learning of Hematopoietic Stem Cell Divisions from Paired Daughter Cell Expression Profiles Reveals Effects of Aging on Self-Renewal

Learning to Reduce Annotation Load

Feed-forwards meet recurrent networks in vehicle trajectory prediction