Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

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.

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 ...

Neurons in the human amygdala and hippocampus are classically thought to encode a person’s identity invariant to visual features. However, it remains largely unknown how visual information from higher visual cortical areas is translated into such a semanti ...

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, ...

Rigid body interactions are fundamental to numerous scientific disciplines, but remain challenging to simulate due to their abrupt nonlinear nature and sensitivity to complex, often unknown environmental factors. These challenges call for adaptable learnin ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce. Likewise, accessin ...

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 ...

This paper introduces MNE-RT, a Python package designed for real-time neural feature extraction from magne-toencephalography (MEG) and electroencephalography (EEG) signals in Brain-Computer Interface (BCI) systems. The package incorporates efficient algori ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Derived from the Karush–Kuhn–Tucker (KKT) optimality conditions of utility maximization, the multiple discrete–continuous extreme value (MDCEV) models are extensively used in the field of time use. This is because they are grounded in a framework that maxi ...

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 ...

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 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 ...

Integrating low-power wearable systems into routine health monitoring is an ongoing challenge. Recent advances in the computation capabilities of wearables make it possible to target complex scenarios by exploiting multiple biosignals and using high-perfor ...

The work presented in this thesis lies at the intersection of Machine Learning (ML) and control theory. The first part is dedicated to the design of Deep Neural Network (DNN) architectures with specific numerical properties, inspired by dynamical systems m ...

Deep digital twins (DDTs) are deep neural networks that encode the behavior of complex physical systems. DDTs are excellent system representations due to their ability to continuously adapt to operational changes and their capability to capture complex rel ...

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

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 ...

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

Chat with Graph Search

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

Feature-based encoding of face identity by single neurons in the human amygdala and hippocampus

Machine Learning for Modeling Stock Returns

Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics

Understanding generalization and robustness in modern deep learning

Probing the latent hierarchical structure of data via diffusion models

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

Advances on Real Time M/EEG Neural Feature Extraction

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

A new flexible multiple discrete–continuous extreme value (MDCEV) choice model: exploring non-monotonic preference in time use decisions

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Partial discharge localization in power transformer tanks using machine learning methods

Deep Learning Theory Through the Lens of Diagonal Linear Networks

M2SKD: Multi-to-Single Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Systems

Navigating the Loop: From Control Systems to Neural Networks and Back

Digital Twin Generalization with Meta and Geometric Deep Learning

On the number of regions of piecewise linear neural networks

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Exploring High-Performance and Energy-Efficient Architectures for Edge AI-Enabled Applications

Topics in statistical physics of high-dimensional machine learning