人工智能资料库：第70辑（20171013）
作者：chen_h
微信号 & QQ：862251340
微信公众号：coderpai
1.【代码】Semantic Segmentation using Fully Convolutional Neural Network
简介：
This repository contains a set of python scripts to train and test semantic segmentation using a fully convolutional neural network. The semantic segmentation network is based on the paper described by Jonathan Long et al.
原文链接：https://github.com/upul/Semantic_Segmentation
2.【博客】Introduction to Model Stacking (with example and codes in Python)
简介：
Stacking, called meta ensembling. is a model ensembling technique used to combine information from multiple predictive models to produce a new one. Often times the stacked model also called the 2nd level model will outperform each of the individual models due to its nature of highlighting each base learner where it performs better and where it performs worse. So, stacking model is used where each base learners are different.
In stacking, the combining mechanism is that the output of the classifiers (Level 1 classifiers) will be used as training data for another classifier (Level 2 classifier) to approximate the same target function. Basically we will just allow the new classifier to figure out the combining mechanism.
原文链接：http://www.datascribble.com/blog/machine-learning/introduction-model-stacking-example-codes-python/
3.【博客】Basics Of Statistics For Machine Learning Engineers
简介：
These days there is a Cambrian explosion of various data science and machine learning tools that make it very easy to start in machine learning. Probably, you are someone who has heard about the buzzword and want to try it out yourself. Maybe you have gone through tutorials on one of the hot and trending machine learning libraries such as scikit-learn and want to have an idea on how to implement machine learning. You recognize that you have all the prerequisites of a problem that make it suitable for machine learning. You have the data set and also a problem that seems to have a pattern to it but you cannot pin it down using an algorithm. You threw the data set to the machine learning library and got something as an outcome.
4.【博客】Artificial Intelligence coursework
简介：
一大波课程
原文链接：https://medium.com/@rameshprasad/artificial-intelligence-coursework-e867f66ae7ff
5.【代码】Tensorflow implementation of paper “unsupervised image to image translation networks”
简介：
In particular, we tried the ‘pix2pix’ model which is the auto-encoder model described in the paper, and also the ‘resnet’ model made up of 9 blocks of resnet (middle blocks are shared). We found that the ‘resnet’ model gives better result than auto-encoder and (slightly) better results than CycleGAN.
Below is a snapshot of our result at the 44th epoch using ‘resnet’ model with default parameters on the horse-zebra dataset. From left to right is: real horse, real zebra, fake zebra, fake horse, cycle horse, cycle zebra.
原文链接：https://github.com/leehomyc/Img2Img-Translation-Networks
算法社区直播课：请点击这里