• Corpus ID: 244130148

A layer-stress learning framework universally augments deep neural network tasks

  title={A layer-stress learning framework universally augments deep neural network tasks},
  author={Shihao Shao and Yong Liu and Qinghua Cui},
Deep neural networks (DNN) such as Multi-Layer Perception (MLP) and Convolutional Neural Networks (CNN) represent one of the most established deep learning algorithms. Given the tremendous effects of the number of hidden layers on network architecture and performance, it is very important to choose the number of hidden layers but still a serious challenge. More importantly, the current network architectures can only process the information from the last layer of the feature extractor, which… 

Figures from this paper



Determining the Number of Hidden Layers in Neural Network by Using Principal Component Analysis

By using Forest Type Mapping Data Set, based on PCA analysis, it was found out that the number of hidden layers that provide the best accuracy was three, in accordance with thenumber of components formed in the principal component analysis which gave a cumulative variance of around 70%.

Convolutional neural networks: an overview and application in radiology

A perspective on the basic concepts of convolutional neural network and its application to various radiological tasks is offered, and its challenges and future directions in the field of radiology are discussed.

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

A new scaling method is proposed that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient and is demonstrated the effectiveness of this method on scaling up MobileNets and ResNet.

Attention is All you Need

A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data

A systematic review of publications using deep learning approaches and neuroimaging data for diagnostic classification of AD found the best classification performance was obtained when multimodal neuroim imaging and fluid biomarkers were combined.

Gradient-based learning applied to document recognition

This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.

Scaling learning algorithms towards AI

It is argued that deep architectures have the potential to generalize in non-local ways, i.e., beyond immediate neighbors, and that this is crucial in order to make progress on the kind of complex tasks required for artificial intelligence.

A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing

A mechanism-driven neural network-based method DeepCE is proposed, which utilizes graph neural network and multi-head attention mechanism to model chemical substructure-Gene and gene-gene associations, for predicting the differential gene expression profile perturbed by de novo chemicals.

Machine-learning-based COVID-19 mortality prediction model and identification of patients at low and high risk of dying

The application of machine-learning-based approaches to predict hospital mortality in patients with COVID-19 and identification of most important predictors from clinical, comorbidities and blood biochemical variables as well as recognizing high- and low-risk CO VID-19 survivors are revealed.