Set up development environment for deep learning

Deep learning has gained a lot of attention because it is particularly good at some type of learning which is very useful for real-world applications. Running some simple examples is a good way to start learning this technique. Setting up a development environment is the first step.

Read more

Compile Async-Await to Generators and Promises

Async/Await is introduced in ES2017. In order to let ES2017 code run in very old browsers/platforms, ES2017 code need to be transpiled/compiled to earlier versions. Async/await need to be transpiled to older-version JavaScript code. In this post, I will list three ways to do the same thing: 1) async/await [ES2017+], 2) generator function + promise … Read more

Neural Network Backpropagation Derivation

I have spent a few days hand-rolling neural networks such as CNN and RNN. This post shows my notes of neural network backpropagation derivation. The derivation of Backpropagation is one of the most complicated algorithms in machine learning. There are many resources for understanding how to compute gradients using backpropagation. But in my opinion, most of them lack a simple example to demonstrate the problem and walk through the algorithm.

Read more