Michael L. PengPrincipal Component AnalysisIn this post, I want to present an intuitive understanding of Principal Component Analysis(PCA) as well as the math foundation behind it…May 25, 20191May 25, 20191
Michael L. PengRethinking ImageNet Pre-trainingA recently published paper Rethinking ImageNet Pre-training by Kaiming He, Ross Girshick, and Piotr dollár shows some interesting…Dec 8, 2018Dec 8, 2018
Michael L. PengMachine Learning Exercise Building A Full PipelineThis blog post is intended for beginner readers and aims to demonstrate the common workflow of building a machine learning pipeline. I…Dec 8, 2018Dec 8, 2018
Michael L. PengImproving neural networks by preventing co-adaptation of feature detectorsThis blog post aims to provide readers some insights on deep neural networks and intuition about dropout technique.May 7, 2018May 7, 2018
Michael L. PengCyclical Learning Rates for Training Neural NetworksLearning rate is one of the most important hyper parameters when it comes to training a neural network. It determines the magnitude of…May 5, 20183May 5, 20183