Robust Ultrasound Travel-time Tomography Using the Bent Ray Model

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.

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

Contemporary AI faces important limitations that remain unresolved despite significant successes. Chief among these are the inability to acquire new knowledge without destroying old, the incomprehensible and nonengineerable nature of internal representatio ...

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

The invention relates to methods for the preparation of method of preparation of Tau aggregates, including fibrils, fibrillar species, soluble and insoluble oligomeric species, new Tau aggregates and uses thereof. The invention further relates to the uses ...

Molecular quantum dynamics simulations are essential for understanding many fundamental phenomena in physics and chemistry. They often require solving the time-dependent Schrödinger equation for molecular nuclei, which is challenging even for medium-sized ...

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 ...

Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in generalization, especially in capturing temporal abstractions for long- horizon tas ...

Given a sequence of functions

f_1,\ldots,f_n

with

f_i:\mathcal{D}\mapsto \mathbb{R}

, finite-sum minimization seeks a point

{x}^\star \in \mathcal{D}

minimizing

\sum_{j=1}^nf_j(x)/n

. In this work, we propose a key twist into the finite-sum minimizat ...

Conventional techniques for purifying macromolecular conjugates often require complex and costly installments that are inaccessible to most laboratories. In this work, we develop a one-step micropreparative method based on a trilayered polyacrylamide gel e ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Background Circadian rhythms regulate cellular physiology and could in fl uence the ef fi cacy of endocrine therapy (ET) in breast cancer (BC). We prospectively tested this hypothesis within the UNIRAD adjuvant phase III trial (NCT01805271). Methods 1278 p ...

Modern optimization is tasked with handling applications of increasingly large scale, chiefly due to the massive amounts of widely available data and the ever-growing reach of Machine Learning. Consequently, this area of research is under steady pressure t ...

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 ...

Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, networks in deep RL must be capable of adapting to new observations and fitting n ...

For a high-dimensional problem, a randomized Gram-Schmidt (RGS) algorithm is beneficial in terms of both computational cost and numerical stability. We apply this dimension reduction technique by random sketching to Krylov subspace methods, e.g., to the ge ...

Curcuminoids and their complexes continue to attract attention in medicinal chemistry, but little attention has been given to their metabolic derivatives. Here, the first examples of (arene)Ru(II) complexes with curcuminoid metabolites, tetrahydrocurcumin ...

Whereas pulse-echo ultrasound imaging relied on focused acoustic waves since its inception, the last two decades have seen the development of techniques based on unfocused waves, including ultrafast ultrasound imaging. In large part due to the emergence of ...

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 ...

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 ...

We describe a novel method to compute the components of dynamo tensors from direct magnetohydrodynamic (MHD) simulations. Our method relies upon an extension and generalization of the standard H & ouml;gbom CLEAN algorithm widely used in radio astronomy to ...

Robust Ultrasound Travel-time Tomography Using the Bent Ray Model

Chat with Graph Search

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Foundations of a New Learning Paradigm in AI Grounded in the Principles of Evolutionary Developmental Biology

Residual-based attention in physics-informed neural networks

Method of preparation of amyloidogenic protein aggregates and uses thereof

High-order geometric integrators for the variational Gaussian wavepacket dynamics and application to vibronic spectra at finite temperature

Deep Learning Theory Through the Lens of Diagonal Linear Networks

SIMPLE HIERARCHICAL PLANNING WITH DIFFUSION

Efficient Continual Finite-Sum Minimization

Micropreparative Gel Electrophoresis for Purification of Nanoscale Bioconjugates

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Association between endocrine adjuvant therapy intake timing and disease-free survival in patients with high-risk early breast cancer: results of a sub-study of the UCBG- UNIRAD trial

Scalable constrained optimization

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

No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO

Randomized flexible GMRES with deflated restarting

Ru(II)-Arene Complexes of Curcumin and Bisdesmethoxycurcumin Metabolites

Inverse Problems in Pulse-Echo Ultrasound: Exploiting Coherence for Image Enhancement and Quantitative Imaging

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Iterative removal of sources to model the turbulent electromotive force