Universal Approximation Property of Hamiltonian Deep Neural Networks

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.

Contemporary artificial intelligence (AI) models' exponentially growing complexity translates to their expanding skill sets. They can create language or image content mimicking human creativity and understanding, becoming indispensable tools in education, ...

Segmenting brain tumors is a critical task in medical imaging that relies on advanced deep-learning methods. However, effectively handling complex tumor regions requires more comprehensive and advanced strategies to overcome challenges such as computationa ...

In this concise contribution, it is demonstrated that Recurrent Neural Networks (RNNs) based on Gated Recurrent Unit (GRU) architecture, possess the capability to learn the complex dynamics of rate-and-state friction (RSF) laws from synthetic data. The dat ...

Having a single neural network to handle a wide and varied range of tasks and modalities has been a long-standing goal. Such a model brings notable advantages, such as test-time computational efficiency, modality fusion, and reduced model size. Our goal in ...

Computing has long been central to technological advancements, where each leap in compute power has catalyzed applications once thought impossible, such as smartphones. Recently, the exponential growth in the compute demand of artificial intelligence (AI) ...

Finding proper collective variables for complex systems and processes is one of the most challenging tasks in simulations, which limits the interpretation of experimental and simulated data and the application of enhanced sampling techniques. Here, we prop ...

Machine translation (MT) systems and language models (LMs) have demonstrated impressive performance in recent years, driven by advances in architecture, algorithms, and the scaling of parameters and training data. Despite the ability of these models to int ...

In this study, we employed traditional methods and deep learning models to improve resolution and quality of low-resolution AFM images made under standard ambient scanning. Both traditional methods and deep learning models were benchmarked and quantified r ...

Research in speech processing has largely focused on source-system modeling, where vocal fold vibrations serve as the source and the vocal cavity's articulations as the system. Nonetheless, speech production includes a complex combination of physiological ...

Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural network architectures, but it is incomplete for neural networks with Hadamar ...

This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) with the ϵ-greedy exploration under the online setting. This problem setting is motivated by the successful deep Q-networks (DQN) framework that fa ...

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for infinite-width 2- ...

In the recent years, Deep Neural Networks (DNNs) have managed to succeed at tasks that previously appeared impossible, such as human-level object recognition, text synthesis, translation, playing games and many more. In spite of these major achievements, o ...

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 ...

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 ...

Large-scale cyber-physical systems require that control policies are distributed, that is, that they only rely on local real-time measurements and communication with neighboring agents. Optimal Distributed Control (ODC) problems are, however, highly intrac ...

We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial loss functions under different adversarial budgets. We then demonstrate tha ...

De novo protein design enhances our understanding of the principles that govern protein folding and interactions, and has the potential to revolutionize biotechnology through the engineering of novel protein functionalities. Despite recent progress in comp ...

Deep neural networks (DNNs) have surpassed human-level accuracy in a variety of cognitive tasks but at the cost of significant memory/time requirements in DNN training. This limits their deployment in energy and memory limited applications that require rea ...

Objective.Mobile Brain/Body Imaging (MoBI) frameworks allowed the research community to find evidence of cortical involvement at walking initiation and during locomotion. However, the decoding of gait patterns from brain signals remains an open challenge. ...

Universal Approximation Property of Hamiltonian Deep Neural Networks

Chat with Graph Search

Programming Light Propagation for Efficient Artificial Intelligence

LIU-NET: lightweight Inception U-Net for efficient brain tumor segmentation from multimodal 3D MRI images

Data-driven dynamic friction models based on Recurrent Neural Networks

Scaling the Modalities in Multimodal Foundation Models

Optical Processors for AI Computing and Networking

Inherent Structural Descriptors Via Machine Learning

From Preprocessing to Evaluation: The Role of External Knowledge in Advancing Language Models and Machine Translation

Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images

Towards Integrated Processing of Physiological Signals and Speech

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration

On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks

Theory of Deep Learning: Neural Tangent Kernel and Beyond

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

On the number of regions of piecewise linear neural networks

Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

De novo protein design by inversion of the AlphaFold structure prediction network

ESSOP: Efficient and Scalable Stochastic Outer Product Architecture for Deep Learning

Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network