Related Experiment Video
Updated: Jun 8, 2026

13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
Deep, big, simple neural nets for handwritten digit recognition
Dan Claudiu Cireşan1, Ueli Meier, Luca Maria Gambardella
1IDSIA, 6928 Manno-Lugano, Switzerland. dan@idsia.ch
Neural Computation
|September 23, 2010
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.
