From Human-Designed Convolutional Neural Networks Towards Robust Neural Architecture Search

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 digitization of 3D deformable objects remains a significant challenge in computer graphics and vision, particularly in the accurate modeling of garments. Garments exhibit complex shape variability, non-rigid deformations, and frequent self-occlusion, m ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Scientific Machine Learning (SciML) is a recently emerged research field which combines physics-based and data-driven models for the numerical approximation of differential problems. Physics-based models rely on the physical understanding of the problem at ...

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 ...

Magnons are the quanta of spin waves and transport angular momenta through magnetically ordered materials. They can be used to distribute and control on-chip GHz signals without charge flow, thereby avoiding Joule heating. Beyond multiplexed signal process ...

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 ...

To retrieve Surface Solar Radiation (SSR) from satellite images, a baseline reflectance of the observed ground in clear-sky conditions, also called background reflectance, is necessary to distinguish atmospheric absorption and scattering effects from surfa ...

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 ...

MammAlps is a multimodal and multi-view dataset of wildlife behavior monitoring. Nine camera-traps were placed at three monitoring sites in the Swiss National Park, from which we curated over 14 hours of video with audio, 2D segmentation maps and 8.5 hours ...

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, ...

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 ...

Jointly estimating hand and object shape facilitates the grasping task in human-to-robot handovers. Relying on handcrafted prior knowledge about the geometric structure of the object fails when generalising to unseen objects, and depth sensors fail to dete ...

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 ...

Estimating ecosystem-atmosphere fluxes such as evapotranspiration (ET) in a robust manner and at a global scale remains a challenge. Methods based on machine learning (ML) have shown promising results in achieving such upscaling, providing a complementary ...

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 ...

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition (ASR) on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are train ...

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 ...

Adversarial examples crafted in black-box scenarios are affected by unrealistic colors or spatial artifacts. To prevent these shortcomings, we propose a novel strategy that generates adversarial images with low detectability and high transferability. The p ...

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 ...

Developing agents that can reliably act on our behalf is central to artificial intelligence (AI). These agents must seamlessly interact with tools, like search engines and databases, and collaborate. In this thesis, we study the abstractions, methods, and ...

From Human-Designed Convolutional Neural Networks Towards Robust Neural Architecture Search

Chat with Graph Search

Neural Garment Modeling

Random matrix methods for high-dimensional machine learning models

Combining physics-based and data-driven models: advancing the frontiers of research with scientific machine learning

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

Perspective on nonvolatile magnon-signal storage and in-memory computation for low-power consuming magnonics

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Retrieval of Surface Solar Radiation through Implicit Albedo Recovery from Temporal Context

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

MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps

Machine Learning for Modeling Stock Returns

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Stereo Hand-Object Reconstruction for Human-to-Robot Handover

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

On the added value of sequential deep learning for the upscaling of evapotranspiration

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

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

Understanding generalization and robustness in modern deep learning

GLoFool: Global Enhancements and Local Perturbations to Craft Adversarial Images

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Collaborative AI Agents in the Era of Large Language Models