Decoupling Backpropagation using Constrained Optimization Methods

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.

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed su ...

Dynamic hand gesture recognition (HGR) is critical for real-time prosthetics and neural robotics applications, where high-density surface electromyography (HD-sEMG) signals provide valuable insights into muscle activity. However, adapting machine learning ...

This paper studies the problem of learning computable functions in the limit by extending Gold's inductive inference framework to incorporate computational observations and restricted input sources. Complimentary to the traditional Input-Output Observation ...

This thesis focuses on the development of advanced algorithmic techniques, primarily Markov Chain Monte Carlo (MCMC) methods, and message passing algorithms, to tackle high-dimensional optimization and inference problems. The algorithms used have a probabi ...

Objective. Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local fi ...

The European Green Deal is prescribing a very ambitious rise in the annual production of renewable energy sources, and grid regulation services are increasingly important in the course of a massive integration of intermittent renewable energy sources. Alth ...

For Graph Neural Networks, oversmoothing denotes the homogenization of vertex embeddings as the number of layers increases. To better understand this phenomenon, we study community detection with a linearized Graph Convolutional Network on the Contextual S ...

Aims. As ground-based all-sky astronomical surveys will gather millions of images in the coming years, a critical requirement emerges for the development of fast deconvolution algorithms capable of efficiently improving the spatial resolution of these imag ...

Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs t ...

Simulations of chemical reactivity in condensed phase systems represent an ongoing challenge in computational chemistry, where traditional quantum chemical approaches typically struggle with both the size of the system and the potential complexity of the r ...

It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge. For example, it ...

The majority of uncertainty quantification methods for deep object detectors are based on the network output, such as sampling strategies like Monte-Carlo dropout or deep ensembles with straight-forward transfers to object detection. Here, we study gradien ...

Transformer-based models have revolutionized NLP. But in general, these models are highly resource consuming. Based on this consideration, several reservoir computing approaches to NLP have shown promising results. In this context, we propose EsnTorch, a l ...

Despite a lack of scientific consensus on the definition of emotions, they are generally considered to involve several modifications in the mind, body, and behavior. Although psychology theories emphasized multi-componential characteristics of emotions, li ...

Persistent Homology (PH) has been successfully used to train networks to detect curvilinear structures and to improve the topological quality of their results. However, existing methods are very global and ignore the location of topological features. In th ...

Structured and grounded representation of text is typically formalized by closed information extraction, the problem of extracting an exhaustive set of (subject, relation, object) triplets that are consistent with a predefined set of entities and relations ...

This paper presents a novel deep learning-based travel behaviour choice model. Our proposed Residual Logit (ResLogit) model formulation seamlessly integrates a Deep Neural Network (DNN) architecture into a multinomial logit model. Recently, DNN models such ...

Field Programmable Gate Arrays (FPGAs) are often used for accelerating machine learning algorithms. These algorithms can be implemented by various architectures which may differ in performance, required area, power consumption and reliability. This paper p ...

Part I of this paper formulated a multitask optimization problem where agents in the network have individual objectives to meet, or individual parameter vectors to estimate, subject to a smoothness condition over the graph. A diffusion strategy was devised ...

Decoupling Backpropagation using Constrained Optimization Methods

Chat with Graph Search

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases

Low-Rank Adaptation for Transformers in Dynamic Hand Gesture Recognition Using High-Density Surface Electromyography

Learning Algorithms in the Limit

Advances in Algorithms for Sampling, Optimization and Inference in Disordered Systems

Neural decoding and feature selection methods for closed-loop control of avoidance behavior

On the modelling of the fatigue-induced damage in Francis turbines start-up sequences

Optimal performance of Graph Convolutional Networks on the Contextual Stochastic Block Model

Ground-based image deconvolution with Swin Transformer UNet

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

Capturing Dichotomic Solvent Behavior in Solute−Solvent Reactions with Neural Network Potentials

Learning sparse features can lead to overfitting in neural networks

Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors

The Esntorch Library: Efficient Implementation of Transformer-based Echo State Networks

Brain networks subserving functional core processes of emotions identified with componential modeling

Data-driven control of room temperature and bidirectional EV charging using deep reinforcement learning: Simulations and experiments

Persistent Homology with Improved Locality Information for more Effective Delineation

GenIE: Generative Information Extraction

ResLogit: A residual neural network logit model for data-driven choice modelling

Runtime Replacement of Machine Learning Modules in Fpga-based Systems

Learning Over Multitask Graphs-Part II: Performance Analysis