本文总结了广告、推荐领域最为流行的10个深度学习CTR模型的结构特点,构建了它们之间的演化图谱。选择模型的标准尽量遵循下面三个原则:
为什么说算法工程师的面试是一门玄学? – 知乎
所以面试通过要满足两个基本要求,一是“技术合格”,二是“愿意一起工作”二者缺一不可。所以在你技能合格的前提下,面试官愿不愿意与你一起工作就成了一个关键且略主观的问题。
但这看似草菅人命的标准其实是有背后的深刻逻辑的。往俗了说叫做看看candidate投不投缘,往大了说叫做符不符合公司文化,往实在了说,是要check你是不是能够顺利的与同事交流协作,得出合理的技术解决方案。
Source: 为什么说算法工程师的面试是一门玄学? – 知乎
重读Youtube深度学习推荐系统论文,字字珠玑,惊为神文 – 知乎
哈哈,我感觉不用写下一篇了,大家直接参考这个答案就可以了。过几天在你这个评论基础上再说的详细一点,非常好的回答。
GitHub – progrium/docker-stress: Docker container for generating workload stress
A Docker container for stress, a tool for generating workload. It can produce CPU, memory, I/O, and disk stress.
Source: GitHub – progrium/docker-stress: Docker container for generating workload stress
GitHub – containerstack/docker-cpustress: CPU stress test tool inside a Docker container
When doing load testing on for example new clusters, I typical use a load generator to generate some “fake” load, however I couldn’t find a simple container image for this job. So thats why I created this simple image to do the job.
Source: GitHub – containerstack/docker-cpustress: CPU stress test tool inside a Docker container
chrstnhntschl/gpu_burn – Docker Hub
A docker image around gpu_burn, a multi-GPU CUDA stress test from http://wili.cc/blog/gpu-burn.html.
I mainly use this tool (with nvidia-docker, https://github.com/NVIDIA/nvidia-docker) to test the power setup of my GPUs in order to make sure that power is enough to run all GPUs at max at the same time.
Machine Learning for iOS
Last Update: January 12, 2018.Curated list of resources for iOS developers in following topics:
Source: Machine Learning for iOS
A Gentle Introduction to Deep Learning for Face Recognition
Given the breakthrough of AlexNet in 2012 for the simpler problem of image classification, there was a flurry of research and publications in 2014 and 2015 on deep learning methods for face recognition. Capabilities quickly achieved near-human-level performance, then exceeded human-level performance on a standard face recognition dataset within a three year period, which is an astounding rate of improvement given the prior decades of effort.
Source: A Gentle Introduction to Deep Learning for Face Recognition
lutzroeder/netron: Visualizer for neural network, deep learning and machine learning models
Visualizer for neural network, deep learning and machine learning models
Source: lutzroeder/netron: Visualizer for neural network, deep learning and machine learning models
RSIS Conference on Foreign Interference Tactics and Countermeasures – Speech by Mr K Shanmugam, Minister for Home Affairs and Minister for Law
What is foreign interference? What are the methods, what is happening now? Essentially, foreign interference is when a country, external agencies, or people try to shape the behaviour, actions, policies of a target country.