Paper to review: ImageNet Classification with Deep Convolutional Neural Networks
[Read More]
Review of LeNet-5: How to design the architecture of CNN
This post is a review of an old, difficult, and inspiring paper: Gradient-Based Learning Applied to Document Recognition”[1] by Yann LeCun as the first author. You can find many reviews of this paper. Most of them only focus on the architecture of the Convolution Neural Network (CNN) LeNet-5. However, I’d...
[Read More]
Overview of optimizers for DNN: when and how to choose which optimizer
In this post, I would like to review the development of optimization methods for deep neural network (DNN) and share suggestions to use optimizers.
[Read More]
Hyper-parameters tuning practices: learning rate, batch size, momentum, and weight decay
Tuning the hyper-parameters of a deep learning (DL) model by grid search or random search is computationally expensive and time consuming. This technical report gives several practical suggestions and steps to choose the optimal hyper-parameters.
[Read More]
Test markdown
Each post also has a subtitle
You can write regular markdown here and Jekyll will automatically convert it to a nice webpage. I strongly encourage you to take 5 minutes to learn how to write in markdown - it’ll teach you how to transform regular text into bold/italics/headings/tables/etc.
[Read More]