Highway Networks
Explore this paper's citation graph
Summary
A new architecture designed to ease gradient-based training of very deep networks, characterized by the use of gating units which learn to regulate the flow of information through a network is introduced.
- Type
- preprint
- Published
- 2015-05-03
- Cited by
- 1,914
- References
- 20
- Access
- Open access
- OpenAlex
- https://openalex.org/W4394643672
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:14786967
Keywords
Computer science, Business
References
- Understanding Locally Competitive Networks
- Understanding the difficulty of training deep feedforward neural networks
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Computational limitations of small-depth circuits
- Long Short-Term Memory
- Going deeper with convolutions
- On the power of small-depth threshold circuits
- Learning to Forget: Continual Prediction with LSTM
- Multi-column deep neural networks for image classification
- A committee of neural networks for traffic sign classification
- ImageNet classification with deep convolutional neural networks
- Representation Learning: A Review and New Perspectives
- On the Number of Linear Regions of Deep Neural Networks
- Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
- Deeply-Supervised Nets
- FitNets: Hints for Thin Deep Nets
- Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Flexible, High Performance Convolutional Neural Networks for Image Classification
Cited by
- Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree
- Training Very Deep Networks
- Assisting the training of deep neural networks with applications to computer vision
- Depth-Gated LSTM
- Behavioral plasticity through the modulation of switch neurons
- Deep Residual Learning for Image Recognition
- The Influence of the Amount of Parameters in Different Layers on the Performance of Deep Learning Models
- Learning Deep Convolutional Neural Networks for Places2 Scene Recognition
- Learning Efficient Algorithms with Hierarchical Attentive Memory
- Predicting Clinical Events by Combining Static and Dynamic Information Using Recurrent Neural Networks
- Gradual DropIn of Layers to Train Very Deep Neural Networks
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size
- Convolution in Convolution for Network in Network
- Domain Adaptation of Recurrent Neural Networks for Natural Language Understanding
- Deep Residual Networks with Exponential Linear Unit
- Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
- Simple2Complex: Global Optimization by Gradient Descent
- Exploiting LSTM structure in deep neural networks for speech recognition
- Residual Networks are Exponential Ensembles of Relatively Shallow Networks
- FractalNet: Ultra-Deep Neural Networks without Residuals
Related papers
- ИСПОЛЬЗОВAНИЕ ПОТЕНЦИAЛA СОЦИAЛЬНЫХ ПAРТНЕРОВ В ПОДГОТОВКЕ БУДУЩИХ ПЕДAГОГОВ
- Using DataGrid Control to Realize DataBase of Querying in VB6.0
- Study and Two Types of Typical Usage of DataGrid Web Server Control
- PACWON: A parallelizing compiler for workstations on a network
- Bidirectional Sort and Choosing a Row to Update or Delete by Click Any Cell in DataGrid
- OpenCL-accelerated object classification in video streams using Spatial Pooler of Hierarchical Temporal Memory
- ESKVS: efficient and secure approach for keyframes-based video summarization framework
- Flexible Application of VSFlexGrid