U-Boost NAS: Utilization-Boosted Differentiable 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 present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...

Federated learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual model updates by nodes also diminishes. In this study, we increase the effe ...

End-to-end learning methods like deep neural networks have been the driving force in the remarkable progress of machine learning in recent years. However, despite their success, the deployment process of such networks in safety-critical use cases, such as ...

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

Forecasting is a capability inherent in humans when navigating. Humans routinely plan their paths, considering the potential future movements of those around them. Similarly, to achieve comparable sophistication and safety, autonomous systems must embrace ...

Pulmonary nodules and masses are crucial imaging features in lung cancer screening that require careful management in clinical diagnosis. Despite the success of deep learning-based medical image segmentation, the robust performance on various sizes of lesi ...

Artificial intelligence, particularly the subfield of machine learning, has seen a paradigm shift towards data-driven models that learn from and adapt to data. This has resulted in unprecedented advancements in various domains such as natural language proc ...

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 ...

Tensor trains are a versatile tool to compress and work with high-dimensional data and functions. In this work we introduce the streaming tensor train approximation (STTA), a new class of algorithms for approximating a given tensor ' in the tensor train fo ...

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 ...

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Monitoring surface cracks in infrastructure is crucial for structural health monitoring. Automatic visual inspection offers an effective solution, especially in hard-to-reach areas. Machine learning approaches have proven their effectiveness but typically ...

Deep neural networks (DNN) have become an essential tool to tackle challenging tasks in many fields of computer science. However, their high computational complexity limits their applicability. Specialized DNN accelerators have been developed to accommodat ...

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 ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretiz ...

Crafting an appealing heading is crucial for attracting readers and marketing work or products. A popular way is to summarize the main idea with a refined description and a memorable acronym. However, there lacks a systematic study and a formal benchmark i ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Dense image-based prediction methods have advanced tremendously in recent years. Their remarkable development has been possible due to the ample availability of real-world imagery. While these methods work well on photographs, their abilities do not genera ...

U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search

Chat with Graph Search

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning

Estimating and Improving the Robustness of Attributions in Text

Deep Learning Generalization with Limited and Noisy Labels

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Scale-Aware Test-Time Click Adaptation for Pulmonary Nodule and Mass Segmentation

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations

Understanding generalization and robustness in modern deep learning

STREAMING TENSOR TRAIN APPROXIMATION

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

Supervised learning and inference of spiking neural networks with temporal coding

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

From classification to segmentation with explainable AI: A study on crack detection and growth monitoring

Hardware-Software Co-design for Improved Resource Utilization in DNN Accelerators

Deep Learning for 3D Surface Modelling and Reconstruction

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design

Unveiling the Art of Heading Design: A Harmonious Blend of Summarization, Neology, and Algorithm

Aggregating Spatial and Photometric Context for Photometric Stereo

Dense Image-based Predictions for Comics Analysis