On Vacuous and Non-Vacuous Generalization Bounds for Deep Neural Networks

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

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 ...

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an ...

Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving differential equations by integrating physical laws into the learning process. This work leverages PINNs to simulate gravitational collapse, a critical phenomenon in astro ...

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

Synthesizability in generative molecular design remains a pressing challenge. Existing methods to assess synthesizability include heuristics-based metrics or retrosynthesis models which predict a synthetic pathway. By contrast, an explicit approach anchors ...

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

To date, galaxy image simulations for weak lensing surveys usually approximate the light profiles of all galaxies as a single or double Sérsic profile, neglecting the influence of galaxy substructures and morphologies deviating from such a simplified param ...

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 ...

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 light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

The Birman-Williams theorem gives a connection between the collection of unstable periodic orbits (UPOs) contained within a chaotic attractor and the topology of that attractor, for three-dimensional systems. In certain cases, the fractal dimension of a ch ...

Machine learning is increasingly integrated with decision making by powering automated systems and informing human decision makers in applications such as CV screening, portfolio allocation, loan risk assessment, and insurance approval. In this thesis, I e ...

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 ...

Overview This dataset provides high-resolution, georeferenced vehicle trajectories collected via drone footage at three roundabouts located in the municipalities of Frick and Laufenburg, Canton of Aargau, Switzerland. The data were collected as part of a ...

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 ...

Photorealistic synthetic data and novel rendering techniques significantly advanced computer vision research. However, datasets focused on computer vision applications cannot be easily applied to robotics because they typically lack physics-related informa ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

Recently, cutting-edge brain-machine interfaces (BMIs) have revealed the potential of decoders such as recurrent neural networks (RNNs) in predicting attempted handwriting [1] or speech [2], enabling rapid communication recovery after paralysis. However, c ...

On Vacuous and Non-Vacuous Generalization Bounds for Deep Neural Networks

Chattez avec Graph Search

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

Gibbs sampling the posterior of neural networks

SPINN: Advancing Cosmological Simulations of Fuzzy Dark Matter with Physics Informed Neural Networks

Graph generative deep learning models with an application to circuit topologies

Directly optimizing for synthesizability in generative molecular design using retrosynthesis models

On the number of regions of piecewise linear neural networks

Euclid preparation: LXVII. Deep learning true galaxy morphologies for weak lensing shear bias calibration

Aggregating Spatial and Photometric Context for Photometric Stereo

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

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

The topology of a chaotic attractor in the Kuramoto-Sivashinsky equation

Machine Learning in Decision-Making Systems: Fairness, Robustness, and Data Bias

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

Vehicle Trajectory Dataset from Drone-Collected Data at Three Swiss Roundabouts

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

GRADE: Generating Realistic and Dynamic Environments for robotics research with Isaac Sim

Incorporating Projective Geometry into Deep Learning

33.3 MiBMI: A 192/512-Channel 2.46mm² Miniaturized Brain-Machine Interface Chipset Enabling 31-Class Brain-to-Text Conversion Through Distinctive Neural Codes