Robust Machine Learning - Distributed Methods for Safe AI

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.

Differences in acquisition protocols or hardware result in measurable changes in image characteristics. These differences affect distributional properties and can also affect the spatial and temporal characteristics of the images. Likewise, the distributio ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

Contemporary AI faces important limitations that remain unresolved despite significant successes. Chief among these are the inability to acquire new knowledge without destroying old, the incomprehensible and nonengineerable nature of internal representatio ...

Deep neural networks (DNNs) are receiving increasing attention in wind power forecasting due to their ability to effectively capture complex patterns in wind data. However, their forecast errors are severely limited by the local optimal weight issue in opt ...

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

Sign Language conveys information through multiple channels composed of manual (handshape, hand movement) and non-manual (facial expression, mouthing, body posture) components. Sign language assessment involves giving granular feedback to a learner, in ter ...

FDTD/FEM simulations, strengthened by machine learning, achieve 95.44% optical absorption efficiency in TiO 2 /TiN plasmonic nanocavities for solar energy harvesting. ...

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

The work presented in this thesis lies at the intersection of Machine Learning (ML) and control theory. The first part is dedicated to the design of Deep Neural Network (DNN) architectures with specific numerical properties, inspired by dynamical systems m ...

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 ...

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 ...

Learning in interdisciplinary spaces is key for generating new models of thinking (Aboelela et al., 2007, p. 341 in Tobi & Kampen, 2018); interdisciplinary thinking nurtures creativity and a critical enquiry of social challenges thanks to the entanglement ...

Proteins are foundational biomolecules of life playing a crucial role in a myriad of biological processes. Their function often requires interplay with other biomolecules, including proteins themselves. Protein-protein interactions (PPIs) are essential for ...

We study the problem of performance optimization of closed -loop control systems with unmodeled dynamics. Bayesian optimization (BO) has been demonstrated to be effective for improving closed -loop performance by automatically tuning controller gains or re ...

Established techniques that enable robots to learn from demonstrations are based on learning a stable dynamical system (DS). To increase the robots' resilience to perturbations during tasks that involve static obstacle avoidance, we propose incorporating b ...

Laser powder bed fusion of metals (PBF-LB/M) is a pivotal additive manufacturing technique that enables the production of intricate components. In addition to enabling the production of complex shapes, it allows for a high degree of freedom in manipulating ...

In today's era of rapid urbanization, smart cities are emerging as a beacon of efficiency and sustainability. At the heart of this evolution is the integration of Machine Learning (ML), which can transform vast streams of data into informed decisions. This ...

Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, networks in deep RL must be capable of adapting to new observations and fitting n ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

Robust Machine Learning - Distributed Methods for Safe AI

Chat with Graph Search

Domain shift, domain adaptation, and generalization: A focus on MRI

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

Foundations of a New Learning Paradigm in AI Grounded in the Principles of Evolutionary Developmental Biology

Improving the accuracy and interpretability of neural networks for wind power forecasting

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Posterior-Based Analysis of Spatio-Temporal Features for Sign Language Assessment

Machine-learning-empowered FDTD/FEM simulations for predictive solar energy absorption in plasmonic metamaterial nanocavity arrays

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Navigating the Loop: From Control Systems to Neural Networks and Back

Deep Learning Theory Through the Lens of Diagonal Linear Networks

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

Designing the Future Workforce through STEAM Education

Engineering novel protein interactions with therapeutic potential using deep learning-guided surface design

Violation-aware contextual Bayesian optimization for controller performance optimization with unmodeled constraints

Learning Barrier-Certified Polynomial Dynamical Systems for Obstacle Avoidance with Robots

Exploring crystallographic texture manipulation in stainless steels via laser powder bed fusion: insights from neutron diffraction and machine learning

From Data to Decision: Exploring Machine Learning's Impact on Shaping Smart Cities

No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO

Meta-learning to address diverse Earth observation problems across resolutions