Training hybrid neural networks with multimode optical nonlinearities using digital twins

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.

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 ...

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, ...

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 ...

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 ...

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 ...

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 ...

Neurons in the human amygdala and hippocampus are classically thought to encode a person’s identity invariant to visual features. However, it remains largely unknown how visual information from higher visual cortical areas is translated into such a semanti ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

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 ...

Deep digital twins (DDTs) are deep neural networks that encode the behavior of complex physical systems. DDTs are excellent system representations due to their ability to continuously adapt to operational changes and their capability to capture complex rel ...

Purpose The aim of this study was to develop a novel approach for predicting the expression status of Epidermal Growth Factor Receptor (EGFR) and its subtypes in patients with Non-Small Cell Lung Cancer (NSCLC) using a Three-Dimensional Convolutional Neura ...

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 ...

Dexterous in-hand manipulation in robotics, particularly with multi-fingered robotic hands, poses significant challenges due to the intricate avoidance of collisions among fingers and the object being manipulated. Collision-free paths for all fingers must ...

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 ...

The rise of robotic body augmentation brings forth new developments that will transform robotics, human-machine interaction, and wearable electronics. Extra robotic limbs, although building upon restorative technologies, bring their own set of challenges i ...

Deploying compute-intensive deep neural networks (DNNs) on resource-constrained end devices has become a prominent trend, enabling localized intelligence. However, efficiently deploying these DNNs at scale poses challenges. To address this, extensive resea ...

With the emergence of ultra-portable ultrasound systems, the need to reduce cost and complexity of ultrasound systems has intensified. Sparse arrays, employing fewer transducer elements to acquire images, offer a viable solution by effectively minimizing d ...

This paper studies the infinite-width limit of deep linear neural networks (NNs) initialized with random parameters. We obtain that, when the number of parameters diverges, the training dynamics converge (in a precise sense) to the dynamics obtained from a ...

The rapid progress of industrial development, urbanization, and traffic has caused air quality degradation that negatively affects human health and environmental sustainability, especially in developed countries. However, due to the limited number of senso ...

Training hybrid neural networks with multimode optical nonlinearities using digital twins

Chattez avec Graph Search

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

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

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

Learning to Assemble with Alternative Plans

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

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

Feature-based encoding of face identity by single neurons in the human amygdala and hippocampus

Safe Deep Neural Networks

On the number of regions of piecewise linear neural networks

Digital Twin Generalization with Meta and Geometric Deep Learning

Advancing EGFR mutation subtypes prediction in NSCLC by combining 3D pretrained ConvNeXt, radiomics, and clinical features

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

Enhancing Dexterity in Confined Spaces: Real-Time Motion Planning for Multifingered In-Hand Manipulation

Gibbs sampling the posterior of neural networks

Investigating neural resource allocation in the sensorimotor control of extra limbs

RAPNet: Resolution-Adaptive and Predictive Early Exit Network for Efficient Image Recognition

Sequential CNN-based Enhancement of Ultrafast Ultrasound Imaging for Sparse Arrays

Infinite-width limit of deep linear neural networks

Self-supervised air quality estimation with graph neural network assistance and attention enhancement