Neural Network Structure Design based on N-Gauss Activation Function
- URL: http://arxiv.org/abs/2106.07562v1
- Date: Tue, 1 Jun 2021 11:16:37 GMT
- Title: Neural Network Structure Design based on N-Gauss Activation Function
- Authors: Xiangri Lu, Hongbin Ma, Jingcheng Zhang
- Abstract summary: We introduce the core block N-Gauss, N-Gauss, and Swish neural network structure design to train MNIST, CIFAR10, and CIFAR100 respectively.
N-Gauss gives full play to the main role of nonlinear modeling of activation functions, so that deep convolutional neural networks have hierarchical nonlinear mapping learning capabilities.
- Score: 0.2578242050187029
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent work has shown that the activation function of the convolutional
neural network can meet the Lipschitz condition, then the corresponding
convolutional neural network structure can be constructed according to the
scale of the data set, and the data set can be trained more deeply, more
accurately and more effectively. In this article, we have accepted the
experimental results and introduced the core block N-Gauss, N-Gauss, and Swish
(Conv1, Conv2, FC1) neural network structure design to train MNIST, CIFAR10,
and CIFAR100 respectively. Experiments show that N-Gauss gives full play to the
main role of nonlinear modeling of activation functions, so that deep
convolutional neural networks have hierarchical nonlinear mapping learning
capabilities. At the same time, the training ability of N-Gauss on simple
one-dimensional channel small data sets is equivalent to the performance of
ReLU and Swish.
Related papers
- ASU-CNN: An Efficient Deep Architecture for Image Classification and
Feature Visualizations [0.0]
Activation functions play a decisive role in determining the capacity of Deep Neural Networks.
In this paper, a Convolutional Neural Network model named as ASU-CNN is proposed.
The network achieved promising results on both training and testing data for the classification of CIFAR-10.
arXiv Detail & Related papers (2023-05-28T16:52:25Z) - Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights.
We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
arXiv Detail & Related papers (2023-02-01T03:18:07Z) - Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a
Polynomial Net Study [55.12108376616355]
The study on NTK has been devoted to typical neural network architectures, but is incomplete for neural networks with Hadamard products (NNs-Hp)
In this work, we derive the finite-width-K formulation for a special class of NNs-Hp, i.e., neural networks.
We prove their equivalence to the kernel regression predictor with the associated NTK, which expands the application scope of NTK.
arXiv Detail & Related papers (2022-09-16T06:36:06Z) - Optimal Learning Rates of Deep Convolutional Neural Networks: Additive
Ridge Functions [19.762318115851617]
We consider the mean squared error analysis for deep convolutional neural networks.
We show that, for additive ridge functions, convolutional neural networks followed by one fully connected layer with ReLU activation functions can reach optimal mini-max rates.
arXiv Detail & Related papers (2022-02-24T14:22:32Z) - Deep Kronecker neural networks: A general framework for neural networks
with adaptive activation functions [4.932130498861987]
We propose a new type of neural networks, Kronecker neural networks (KNNs), that form a general framework for neural networks with adaptive activation functions.
Under suitable conditions, KNNs induce a faster decay of the loss than that by the feed-forward networks.
arXiv Detail & Related papers (2021-05-20T04:54:57Z) - Non-linear Functional Modeling using Neural Networks [6.624726878647541]
We introduce a new class of non-linear models for functional data based on neural networks.
We propose two variations of our framework: a functional neural network with continuous hidden layers, and a second version that utilizes basis expansions and continuous hidden layers.
arXiv Detail & Related papers (2021-04-19T14:59:55Z) - Exploiting Heterogeneity in Operational Neural Networks by Synaptic
Plasticity [87.32169414230822]
Recently proposed network model, Operational Neural Networks (ONNs), can generalize the conventional Convolutional Neural Networks (CNNs)
In this study the focus is drawn on searching the best-possible operator set(s) for the hidden neurons of the network based on the Synaptic Plasticity paradigm that poses the essential learning theory in biological neurons.
Experimental results over highly challenging problems demonstrate that the elite ONNs even with few neurons and layers can achieve a superior learning performance than GIS-based ONNs.
arXiv Detail & Related papers (2020-08-21T19:03:23Z) - Modeling from Features: a Mean-field Framework for Over-parameterized
Deep Neural Networks [54.27962244835622]
This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs)
In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit.
We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
arXiv Detail & Related papers (2020-07-03T01:37:16Z) - FastONN -- Python based open-source GPU implementation for Operational
Neural Networks [25.838282412957675]
This work introduces a fast GPU-enabled library for training operational neural networks, FastONN.
FastONN is based on a novel vectorized formulation of the operational neurons.
bundled auxiliary modules offer interfaces for performance tracking and checkpointing across different data partitions and customized metrics.
arXiv Detail & Related papers (2020-06-03T13:33:35Z) - Self-Organized Operational Neural Networks with Generative Neurons [87.32169414230822]
ONNs are heterogenous networks with a generalized neuron model that can encapsulate any set of non-linear operators.
We propose Self-organized ONNs (Self-ONNs) with generative neurons that have the ability to adapt (optimize) the nodal operator of each connection.
arXiv Detail & Related papers (2020-04-24T14:37:56Z) - Rectified Linear Postsynaptic Potential Function for Backpropagation in
Deep Spiking Neural Networks [55.0627904986664]
Spiking Neural Networks (SNNs) usetemporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-power event-driven neuromorphic implementation.
This paper investigates the contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.
arXiv Detail & Related papers (2020-03-26T11:13:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.