Learning Approach to Optical Tomography

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.

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

Silicate glasses have played a major role as structural and functional materials in human civilization since ancient Egypt. Despite their widespread use and importance in modern society, silica glasses with complex geometries are only fabricated in automat ...

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits. In th ...

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 ...

Optical microscopy is an essential tool for biologists, who are often faced with the need to overcome the spatial and temporal resolution limitations of their devices to capture finer details. As upgrading imaging hardware is expensive, computational metho ...

Deep neural networks trained on physical losses are emerging as promising surrogates for nonlinear numerical solvers. These tools can predict solutions to Maxwell's equations and compute gradients of output fields with respect to the material and geometric ...

A Phase-contrast imaging (PCI) diagnostic provides measurements of line-integrated electron density fluctuations. Localisation along the laser beam path can be achieved with a spatial filter that selects the wave-vector directions of the fluctuations contr ...

In the past decade, optical diffraction tomography has gained a lot of attention for its ability to create label-free three-dimensional (3D) images of the refractive index distribution of biological samples using scattered fields measured through holograph ...

Reading out neuronal activity from three-dimensional (3D) functional imaging requires segmenting and tracking individual neurons. This is challenging in behaving animals if the brain moves and deforms. The traditional approach is to train a convolutional n ...

Artificial Neural Networks (ANN) are habitually trained via the back-propagation (BP) algorithm. This approach has been extremely successful: Current models like GPT-3 have O(10 11 ) parameters, are trained on O(10 11 ) words and produce awe-inspiring resu ...

Preserving privacy is a growing concern in our society where cameras are ubiquitous. In this work, we propose a trainable image acquisition method that removes the sensitive information in the optical domain before it reaches the image sensor. The method b ...

Hyperdimensional (HD) computing is a novel approach to machine learning inspired by neuroscience, which uses vectors in a hyper-dimensional space to represent data and models. This approach has gained significant interest in recent years with applications ...

To obtain a more complete understanding of material microstructure at the nanoscale and to gain profound insights into their properties, there is a growing need for more efficient and precise methods that can streamline the process of 3D imaging using a tr ...

In recent years, there has been a significant revolution in the field of deep learning, which has demonstrated its effectiveness in automatically capturing intricate patterns from large datasets. However, the majority of these successes in Computer Vision ...

We propose a method for adapting neural networks to distribution shifts at test-time. In contrast to training-time robustness mechanisms that attempt to anticipate and counter the shift, we create a closed-loop system and make use of test-time feedback sig ...

We investigate methods for manipulating classifier explanations while keeping the predictions unchanged. Our focus is on using a sparse attack, which seeks to alter only a minimal number of input features. We present an efficient and novel algorithm for co ...

In the current deep learning paradigm, the amount and quality of training data are as critical as the network architecture and its training details. However, collecting, processing, and annotating real data at scale is difficult, expensive, and time-consum ...

Learning Approach to Optical Tomography

Chat with Graph Search

Driving and suppressing the human language network using large language models

Multimaterial Volumetric Printing of Silica-Based Glasses

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Practical computational imaging by use of spatiotemporal light modulation: from simulations to applications in biological microscopy

Predicting nonlinear optical scattering with physics-driven neural networks

A synthetic phase-contrast imaging diagnostic with spatial filtering for gyrokinetic simulations

Exploring Novel Modalities for Optical Diffraction Tomography

Automated neuron tracking inside moving and deforming C. elegans using deep learning and targeted augmentation

Artificial Neural Network Training on an Optical Processor via Direct Feedback Alignment

Privacy-Preserving Image Acquisition for Neural Vision Systems

Hyperdimensional computing for biosignal monitoring: Applications for epilepsy detection

3D reconstruction of curvilinear one-dimensional objects viewed in transmission electron microscopy

Deep Learning for 3D Surface Modelling and Reconstruction

Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback

Sparse Attacks for Manipulating Explanations in Deep Neural Network Models

AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration