Publication

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

Résumé

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 Hadamard products (NNs-Hp), e.g., StyleGAN and polynomial neural networks (PNNs). In this work, we derive the finite-width NTK formulation for a special class of NNs-Hp, i.e., polynomial neural networks. We prove their equivalence to the kernel regression predictor with the associated NTK, which expands the application scope of NTK. Based on our results, we elucidate the separation of PNNs over standard neural networks with respect to extrapolation and spectral bias. Our two key insights are that when compared to standard neural networks, PNNs can fit more complicated functions in the extrapolation regime and admit a slower eigenvalue decay of the respective NTK, leading to a faster learning towards high-frequency functions. Besides, our theoretical results can be extended to other types of NNs-Hp, which expand the scope of our work. Our empirical results validate the separations in broader classes of NNs-Hp, which provide a good justification for a deeper understanding of neural architectures.

À propos de ce résultat
Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.
Concepts associés (34)
Réseau de neurones artificiels
Un réseau de neurones artificiels, ou réseau neuronal artificiel, est un système dont la conception est à l'origine schématiquement inspirée du fonctionnement des neurones biologiques, et qui par la suite s'est rapproché des méthodes statistiques. Les réseaux de neurones sont généralement optimisés par des méthodes d'apprentissage de type probabiliste, en particulier bayésien.
Réseau neuronal convolutif
En apprentissage automatique, un réseau de neurones convolutifs ou réseau de neurones à convolution (en anglais CNN ou ConvNet pour convolutional neural networks) est un type de réseau de neurones artificiels acycliques (feed-forward), dans lequel le motif de connexion entre les neurones est inspiré par le cortex visuel des animaux. Les neurones de cette région du cerveau sont arrangés de sorte qu'ils correspondent à des régions qui se chevauchent lors du pavage du champ visuel.
Types of artificial neural networks
There are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.
Afficher plus
Publications associées (163)

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of 22-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...
EPFL2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Volkan Cevher, Grigorios Chrysos, Fanghui Liu

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 ...
2024

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

Alexander Mathis, Alberto Silvio Chiappa, Alessandro Marin Vargas, Axel Bisi

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 ...
EPFL Infoscience2024
Afficher plus
MOOCs associés (17)
Neuronal Dynamics 2- Computational Neuroscience: Neuronal Dynamics of Cognition
This course explains the mathematical and computational models that are used in the field of theoretical neuroscience to analyze the collective dynamics of thousands of interacting neurons.
Neuronal Dynamics 2- Computational Neuroscience: Neuronal Dynamics of Cognition
This course explains the mathematical and computational models that are used in the field of theoretical neuroscience to analyze the collective dynamics of thousands of interacting neurons.
Neuronal Dynamics - Computational Neuroscience of Single Neurons
The activity of neurons in the brain and the code used by these neurons is described by mathematical neuron models at different levels of detail.
Afficher plus