Deep Learning Theory Through the Lens of Diagonal Linear 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.

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 ...

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 ...

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 ...

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

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 ...

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 ...

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 ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

Animals have to navigate complex environments and perform intricate swimming maneuvers in the real world. To conquer these challenges, animals evolved a variety of motion control strategies. While it is known that many factors contribute to motion control, ...

Now is an exciting time for the domain of Earth observation (EO), with a multitude of diverse sensors looking at the planet from satellites, airplanes or drones. The volume of imagery acquired is massive, and hold great potential for a variety of applicati ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

Facial paralysis is a highly burdening condition, resulting in a patient's inability to move his musculature on one or both sides of the mouth. The restoration of facial movement is crucial for enhancing the overall patients' quality of life. The use of DE ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

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 ...

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 ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

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 ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce. Likewise, accessin ...

Rigid body interactions are fundamental to numerous scientific disciplines, but remain challenging to simulate due to their abrupt nonlinear nature and sensitivity to complex, often unknown environmental factors. These challenges call for adaptable learnin ...

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Chattez avec Graph Search

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

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

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

Learning to Assemble with Alternative Plans

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

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

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

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Using deep reinforcement learning to investigate stretch feedback during swimming of the lamprey

Interact with Earth Observation Images using AI: Transparent Methods and Evaluation for Visual Question Answering

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

DEMO: Dielectric elastomer actuators (DEAs) for the restoration of facial movements

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

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

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

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

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

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Probing the latent hierarchical structure of data via diffusion models

Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics