Spatially-sparse convolutional neural networks
Explore this paper's citation graph
Summary
A CNN for processing spatially-sparse inputs, motivated by the problem of online handwriting recognition, and applying a deep convolutional network using sparsity has resulted in a substantial reduction in test error on the CIFAR small picture datasets.
- Type
- preprint
- Published
- 2014-09-21
- Cited by
- 246
- References
- 14
- Access
- Open access
- OpenAlex
- https://openalex.org/W189277179
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:14731791
Keywords
Computer science, Convolutional neural network, Artificial intelligence, Pattern recognition (psychology), Padding
References
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Improving neural networks by preventing co-adaptation of feature detectors
- Going deeper with convolutions
- Word-level training of a handwritten word recognizer based on convolutional neural networks
- A study on the use of 8-directional features for online handwritten Chinese character recognition
- Learning methods for generic object recognition with invariance to pose and lighting
- Multi-column deep neural networks for image classification
- CASIA Online and Offline Chinese Handwriting Databases
- ImageNet classification with deep convolutional neural networks
- Network In Network
- Rectifier Nonlinearities Improve Neural Network Acoustic Models
- Network In Network
- UCI Machine Learning Repository
- The mnist database of handwritten digits
- Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Convolutional Neural Networks for Human Action Recognition
Cited by
- A Bayesian encourages dropout
- Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video
- Training Very Deep Networks
- PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
- ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
- Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks
- BinaryConnect: Training Deep Neural Networks with binary weights during propagations
- Channel-Max, Channel-Drop and Stochastic Max-pooling
- Sparse 3D convolutional neural networks
- Fractional Max-Pooling
- Relaxing from Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging
- Direction histogram: novel discriminative global feature for Thai offline handwritten OCR
- A novel activation function for multilayer feed-forward neural networks
- Convolutional Tables Ensemble: classification in microseconds
- A novel neuroscience-inspired architecture: For computer vision applications
- Genetic Architect: Discovering Genomic Structure with Learned Neural Architectures
- Gelatinous zooplankton in marine communities and ecosystems: Fine-scale horizontal and vertical distribution, trophic drivers, and contribution to global carbon cycling
- Deeply-Fused Nets
- Refining Architectures of Deep Convolutional Neural Networks
- Steganalysis via a Convolutional Neural Network using Large Convolution Filters
Related papers
- The Effect of Padding Foam on the Compression Characteristics of Some Agglomerated Food Powders
- Deep Convolution Neural Network for RBC Images
- Leaf Features Extraction for Plant Classification using CNN
- Deep CNN models for pulmonary nodule classification: Model modification, model integration, and transfer learning
- Automated Fruit Classification Using Deep Convolutional Neural Network
- Small aircraft detection using deep learning
- An Improved Approach for Fire Detection using Deep Learning Models