Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks

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.

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 ...

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 ...

Decentralized learning (DL) is an emerging approach that enables nodes to collaboratively train a machine learning model without sharing raw data. In many application domains, such as healthcare, this approach faces challenges due to the high level of hete ...

When arranged in a crossbar configuration, resistive memory devices can be used to execute Matrix-Vector Multiplications (MVMs), the most dominant operation of many Machine Learning (ML) algorithms, in constant time complexity. Nonetheless, when performing ...

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 ...

When a plasma disrupts in a tokamak, significant heat and electromagnetic loads are deposited onto the surrounding device components. These forces scale with plasma current and magnetic field strength, making disruptions one of the key challenges for futur ...

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

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 ...

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 ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

Neural networks have shown to be a powerful tool to represent the ground state of quantum many-body systems, including fermionic systems. However, efficiently integrating lattice symmetries into neural representations remains a significant challenge. In th ...

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

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 ...

Cyclic peptides are attractive for drug discovery due to their excellent binding properties and the potential to cross cell membranes. However, by far not all cyclic peptides are cell permeable, and measuring or predicting their membrane permeability is no ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time horizon. Due to the t ...

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks

Chat with Graph Search

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Fair Decentralized Learning

LIONHEART: A Layer-based Mapping Framework for Heterogeneous Systems with Analog In-Memory Computing Tiles

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Plasma state monitoring and disruption characterization using multimodal VAEs

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

Generalization of Scaled Deep ResNets in the Mean-Field Regime

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

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations

Person Re-Identification and its Application to Multi-Object Tracking

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

Bulk measurement of membrane permeability for random cyclic peptides in living cells to guide drug development

Robust NAS under adversarial training: benchmark, theory, and beyond

A learning-based approach to stochastic optimal control under reach-avoid constraint