Understanding generalization and robustness in modern deep learning

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.

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

Deriving health indicators of rotating machines is crucial for their maintenance. However, this process is challenging for the prevalent adopted intelligent methods since they may take the whole data distributions, not only introducing noise interference b ...

The process of protein aggregation, central to neurodegenerative diseases like Huntington’s, is challenging to study due to its unpredictable nature and relatively rapid kinetics. Understanding its biomechanics is crucial for unraveling its role in disease ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

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 ...

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 ...

A range of behavioral and contextual factors, including eating and drinking behavior, mood, social context, and other daily activities, can significantly impact an individual's quality of life and overall well-being. Therefore, inferring everyday life aspe ...

Visual affordance segmentation identifies image regions of an object an agent can interact with. Existing methods re-use and adapt learning-based architectures for semantic segmentation to the affordance segmentation task and evaluate on small-size dataset ...

Web search engines process billions of queries daily, making the balance between computational efficiency and ranking quality crucial. While neural ranking models have shown impressive performance, their computational costs, particularly in feature extract ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

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 ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

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 ...

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 ...

Traditional control approaches heavily rely on hard-coded expert knowledge, complicating the development of optimal control solutions as system complexity increases. Deep Reinforcement Learning (DRL) offers a selflearning control solution, proving advantag ...

Machine learning has provided a means to accelerate early-stage drug discovery by combining molecule generation and filtering steps in a single architecture that leverages the experience and design preferences of medicinal chemists. However, designing mach ...

Understanding the structure of real data is paramount in advancing modern deep-learning methodologies. Natural data such as images are believed to be composed of features organized in a hierarchical and combinatorial manner, which neural networks capture d ...

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consu ...

This dataset contains a collection of ultrafast ultrasound acquisitions from nine volunteers and the CIRS 054G phantom. For a comprehensive understanding of the dataset, please refer to the paper: Viñals, R.; Thiran, J.-P. A KL Divergence-Based Loss for In ...

Animals exhibit remarkable locomotion skills despite significant sensorimotor delays and operating in uncertain environments. Moreover, mammals acquire these skills within minutes of birth. From the Cambrian explosion to the present day, vertebrate motor c ...

Understanding generalization and robustness in modern deep learning

Chat with Graph Search

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

Classifier-free diffusion-based weakly-supervised approach for health indicator derivation in rotating machines: Advancing early fault detection and condition monitoring

Self-driving microscopy detects the onset of protein aggregation and enables intelligent Brillouin imaging

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Fair Decentralized Learning

Scalable constrained optimization

Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life

Segmenting Object Affordances: Reproducibility and Sensitivity to Scale

Cost-Efficiency Trade-offs for Neural Cascade Rankers in Web Search

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

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

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

A trustworthy reinforcement learning framework for autonomous control of a large-scale complex heating system: Simulation and field implementation

Machine learning-aided generative molecular design

A phase transition in diffusion models reveals the hierarchical nature of data

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning: Dataset (1/6)

A Bio-Inspired Learning and Control Framework for Cross-Embodiment and Cross-Task Locomotion