Improving the Training of Compact Neural Networks for Visual Recognition

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.

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 ...

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 ...

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 ...

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 ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

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 ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

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 ...

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

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, ...

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 ...

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 recent years, neural quantum states have emerged as a powerful variational approach, achieving state-of-the-art accuracy when representing the ground-state wave function of a great variety of quantum many-body systems, including spin lattices, interacti ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

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 ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

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 ...

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 ...

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 ...

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 ...

Improving the Training of Compact Neural Networks for Visual Recognition

Chat with Graph Search

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

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

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

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

Random matrix methods for high-dimensional machine learning models

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

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Learning to Assemble with Alternative Plans

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

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

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

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

Accurate neural quantum states for interacting lattice bosons

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

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

Machine Learning for Modeling Stock Returns

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

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

Probing the latent hierarchical structure of data via diffusion models

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