作者：chen_h
微信号 & QQ：862251340
微信公众号：coderpai
1.【博客】Research Progress and Application of Convolutional Neural Network
简介：
Convolutional Neural Network (CNN) has been proven to be the best solution for image recognition. The paper introduced the process in which it is generated from Computer Vision and multilayer perceptrons, and the core concepts, convolution and pooling, which also comes from Computer Vision. CNN has some advantages like fast processing and high accuracy, but the cost of training is also high and it is a black box, which is not easy to tell the meanings of the hidden layers. Transfer learning could bring another kind of spirit into CNN, which is based on pre-trained networks, aims to solve general problems and reduces training cost.
2.【博客】How to debug neural networks. Manual.
简介：
Debugging neural networks can be a tough job even for field expert. Millions of parameters stuck together where even one small change can break all your hard work. Without debugging and visualization all your actions is popping a coin, and what worse it eating your time. Here i gather practices that will help you find problems earlier.
原文链接：https://medium.com/machine-learning-world/how-to-debug-neural-networks-manual-dc2a200f10f2
3.【博客】How To Become A Machine Learning Engineer: Learning Path
简介：
We will walk you through all the aspects of machine learning from simple linear regressions to the latest neural networks, and you will learn not only how to use them but also how to build them from scratch.
Big part of this path is oriented on Computer Vision(CV), because it’s the fastest way to get general knowledge, and the experience from CV can be simply transferred to any ML area.
原文链接：https://medium.com/machine-learning-world/learning-path-for-machine-learning-engineer-a7d5dc9de4a4
4.【博客】Gradient Trader Part 1: The Surprising Usefulness of Autoencoders
简介：
This post is about a simple tool in deep learning toolbox: Autoencoder. It can be applied to multi-dimensional financial time series.
5.【博客】Deblur Photos Using Generic Pix2Pix
简介：
Last week my partner came across a problem at work. There were some poorly shot photos that were quite blurry and needed to be repaired. Unsharp masking didn’t work well, along with a few free reparing softwares. The problem was solved by manually recreate important parts of the photo using Photoshop. But I couldn’t help but wonder if deblurring can be done via some generic deep learning algorithms.
原文链接：https://medium.com/machine-learning-world/deblur-photos-using-generic-pix2pix-6f8774f9701e
算法社区直播课：请点击这里