Deep, Big, Simple Neural Nets for Handwritten Digit Recognition-Reference-Cited by-同舟云学术

Deep, Big, Simple Neural Nets for Handwritten Digit Recognition

Published:2010-12 Issue:12 Volume:22 Page:3207-3220
ISSN:0899-7667
Container-title:Neural Computation
language:en
Short-container-title:Neural Computation

Author:

Cireşan Dan Claudiu¹,Meier Ueli¹,Gambardella Luca Maria¹,Schmidhuber Jürgen¹

Affiliation:

1. IDSIA, 6928 Manno-Lugano, Switzerland, and University of Lugano, 6900 Lugano, Switzerland, and Sculoa universitaria professionale della svizzera italiana, 6928 Manno-Lugano, Switzerland

Abstract

Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning.

Publisher

MIT Press - Journals

Subject

Cognitive Neuroscience,Arts and Humanities (miscellaneous)

Link

https://www.mitpressjournals.org/doi/pdf/10.1162/NECO_a_00052

Reference18 articles.

1. To recognize shapes, first learn to generate images

2. Reducing the Dimensionality of Data with Neural Networks

Cited by 608 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Byzantine-robust Federated Learning via Cosine Similarity Aggregation;Computer Networks;2024-12

2. A self-supervised learning framework based on masked autoencoder for complex wafer bin map classification;Expert Systems with Applications;2024-09

3. Monitoring framework development for a network of multiple laboratory structures;Journal of Building Engineering;2024-09

4. Towards a bilipschitz invariant theory;Applied and Computational Harmonic Analysis;2024-09

5. Towards a More Robust and Accurate OCR Model with Adversarial Techniques in HMI Testing Scenarios;2024 IEEE Conference on Artificial Intelligence (CAI);2024-06-25