Blog posts


Training LeNet-5 model on the CIFAR-10 in Julia

10 minute read


LeNet-5 is a convolutional neural network (CNN) that was introduced by Yann LeCun et al. in their 1998 paper, “Gradient-Based Learning Applied to Document Recognition.” It was one of the first successful applications of CNNs on a large-scale image recognition task, and it is still widely used today as a starting point for many image recognition tasks. picture 1
[1] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, november 1998. Read more