【目标识别】深度学习进行目标识别的资源列表：O网页链接 包括RNN、MultiBox、SPP-Net、DeepID-Net、Fast R-CNN、DeepBox、MR-CNN、Faster R-CNN、YOLO、DenseBox、SSD、Inside-Outside Net、G-CNN
'机器学习笔记' by 李金 GitHub: O网页链接
"vbmfa: Variational Bayesian Mixture of Factor Analysers" O网页链接
'Julia AutoDiff - some basic Julia code for AutoDiff' by davidbarber GitHub: O网页链接
《Announcing TensorFlow 0.8 – now with distributed computing support! | Google Research Blog》by Derek Murray O网页链接
"Machine Learning workshop series hosted by UCLU Technology Society" Supervised Learning:O网页链接 Unsupervised Learning:O网页链接 Deep Learning:O网页链接
'distribution_diagrams - R-script for generating canonical diagrams of distributions to be used to describe Bayesian hierarchical models.' by Rasmus Bååth GitHub: O网页链接
《Better Feature Engineering with Spark, Solr, and Lucene Analyzers》by Lucidworks O网页链接
《Popular Deep Learning Libraries | Machine Learning Mastery》by Jason Brownlee O网页链接
《A C++ library for Multimodal Deep Learning》J Jin [Johns Hopkins University] (2016) O网页链接 GitHub:O网页链接
'Torch implementation of Sequence to Sequence Learning with Neural Networks' by Vladimir Ivanov GitHub: O网页链接
《Metrics for Community Analysis: A Survey》T Chakraborty, A Dalmia, A Mukherjee, N Ganguly [University of Maryland] (2016) O网页链接
机器如何自动产生对联？这篇文章介绍了一种可能的思路。"使用Encoder-Decoder模型自动生成对联的思路 " O网页链接
完成了一篇“Auto-Encoding Variational Bayes”论文笔记。感觉这个框架很好，用NN来模拟VB中的各种后验和似然函数，设计一个可以求导的变分推断，通过BP算来优化下界。O网页链接
为什么基于贝叶斯优化的自动调参没有大范围使用？ - 7 个回答, 127 人关注 O为什么基于贝叶斯优化的自动调参没有大范围使...（O网页链接
"Tensorflow Playground - interactive visualization of neural networks, written in typescript using d3.js" O网页链接 GitHub:O网页链接 《Play With the Inner Workings of a Neural Network on This Neat Website》by Jamie Condliffe O网页链接
【BBO生物地理学优化算法】Biogeography-based optimization（BBO）：08年被首次在IEEE上提出来的。它是在遗传算法和粒子群它是在遗传算法和粒子群算法的基础上发展来的。适用于解决高维度的，多目标的最优化问题。O网页链接 O网页链接
