9405
showing only twitter_favs [see all]
Twitter
CLion started 2018.3 EAP with the initial remote development support. Compile, run/debug app or tests on a remote m…
from twitter_favs
4 days ago
Help! I can’t reproduce a machine learning project! | No Free Hunch
“Help! I can’t reproduce a machine learning project!” - nice blog post from
from twitter_favs
4 days ago
Twitter
I enjoyed looking at Xiao-Li Meng's extraordinary paper on big data and bias,

Amazing jou…
from twitter_favs
5 days ago
Twitter
(7) Monitor your gradients and your weights. Check them often.

NNs frequently fail because weights get very, very…
from twitter_favs
5 days ago
Twitter
(6) Another attempt to combat overfitting: make sure to add dropout layers. ⚖

Dropout layers set a certain percent…
from twitter_favs
5 days ago
Twitter
(5) ☠ WEIGHT INITIALIZATION ☠

Your weight initialization randomization function needs to be carefully chosen and s…
from twitter_favs
5 days ago
Twitter
(4) More layers isn't always better! And adding too many of 'em at the beginning often leads to overfitting. 🙅‍♀️…
from twitter_favs
5 days ago
Twitter
(2) Use small, random batches to train rather than the entire dataset.

⏳Reducing your batch size increases trainin…
from twitter_favs
5 days ago
Twitter
After Python 3, Pipenv is the best thing happened to the Python community.
from twitter_favs
6 days ago
Twitter
【How to be a rocket ship】创业公司资源有限,更要讲求工作效率了。工作别刷社交网络,可以给自己些心理暗示,如完成一小任务(如提交小段代码)、奖励自己去冲个咖啡啥的。这里浪费五分钟那里浪费五分钟,积少成多起来就…
from twitter_favs
8 days ago
Twitter
Awesome collaboration with the team using ML to save phone battery on Android Pie... so many cool, very pr…
from twitter_favs
8 days ago
Twitter
if you missed his recent twitter thread, here's the story of 's experience publishing his latest bo…
from twitter_favs
11 days ago
Twitter
Not really- callbacks must run to completion with no errors - non-terminating callbacks or fatal errors in callback…
from twitter_favs
12 days ago
Twitter
Optimizing CNN Model Inference on CPUs.
from twitter_favs
12 days ago
Twitter
Selective Refinement Network for High Performance Face Detection.
from twitter_favs
12 days ago
[1809.03685] Massively Parallel Dynamic Programming on Trees
"Massively Parallel Dynamic Programming on Trees," Bateni et al.:
from twitter_favs
12 days ago
Twitter
Chatted about my journey through AI, including stories from early days of Google Brain & Coursera, plus Landing AI…
from twitter_favs
12 days ago
The use of embeddings in OpenAI Five | Computational Neuroscience Lab
A good analysis of the embeddings we use in the OpenAI Five model: . After analyzing the res…
from twitter_favs
12 days ago
Twitter
A good analysis of the embeddings we use in the OpenAI Five model: . After analyzing the res…
from twitter_favs
12 days ago
Twitter
Learn more about Google’s Service Infrastructure from an engineer who helped build it. chats with Su Fu,…
from twitter_favs
12 days ago
Twitter
RT : There is always more to read than you have time for. A trick I have is to set a topic each week, and mercilessly ig…
from twitter_favs
12 days ago
Twitter
A key to greater productivity in CLion is a keyboard-centric approach! Check the Key Promoter X plugin to help you…
from twitter_favs
13 days ago
Twitter
Great article: “When Bayes, Ockham, and Shannon come together to define machine learning” by Tirthajyoti Sarkar.…
from twitter_favs
13 days ago
Twitter
新的博客文章《如何降低软件的复杂性?》:John Ousterhout 是斯坦福大学计算机系教授,出版了一本新书《软件设计的哲学》。

大部分书教你怎么写正确的代码,这本书教你如何正确设计软件。…
from twitter_favs
13 days ago
Twitter
I suspect we might all have been guilty of this at some point - there is no substitute for having solid tests in pl…
from twitter_favs
13 days ago
Twitter
Dangerous habit: Play around with an algorithm in a Jupyter notebook and check if the output looks “reasonable” ins…
from twitter_favs
14 days ago
Untitled (https://www.youtube.com/watch?v=FihU5JxmnBg)
Debugging is not about tools, it is about method -- the scientific method.
from twitter_favs
14 days ago
Twitter
Debugging is not about tools, it is about method -- the scientific method.
from twitter_favs
14 days ago
MELPA
org-web-tools (20180903.734) --- Display and capture web content with Org-mode
from twitter_favs
15 days ago
Twitter
Thomas Funkhauser talking about Deep Depth Completion via normals-to-Depth formulation
from twitter_favs
15 days ago
Untitled (https://www.youtube.com/watch?v=P9u8x13W7UE)
Hmmmm. Spending a lot of time pondering the RustCon closing keynote. Wondering if I shoul…
from twitter_favs
15 days ago
Twitter
Hmmmm. Spending a lot of time pondering the RustCon closing keynote. Wondering if I shoul…
from twitter_favs
15 days ago
[1809.01819] CASC: Context-Aware Segmentation and Clustering for Motif Discovery in Noisy Time Series Data
CASC: Context-Aware Segmentation and Clustering for Motif Discovery in Noisy Time Series...
from twitter_favs
16 days ago
Twitter
CASC: Context-Aware Segmentation and Clustering for Motif Discovery in Noisy Time Series...
from twitter_favs
16 days ago
[1809.01791] MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection
MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Dete...
from twitter_favs
16 days ago
Twitter
MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Dete...
from twitter_favs
16 days ago
Twitter
In software, naming matters, because names reflect how you think about a problem. Code is also communication, and n…
from twitter_favs
16 days ago
Twitter
Unpopular opinion: to really make it as a senior/lead engineer, you have to get good at soaking up interruptions, o…
from twitter_favs
16 days ago
Untitled (https://www.youtube.com/watch?v=oyLBGkS5ICk)
"Breaking changes are broken." If you are still using semantic versioning, please watch
from twitter_favs
16 days ago
Twitter
"Breaking changes are broken." If you are still using semantic versioning, please watch
from twitter_favs
16 days ago
(429) https://twitter.com/i/web/status/1038035984649256961
Frustrated with the difficulty of versioning Jupyter notebooks and the confusion from out-of-order execution? We ad…
from twitter_favs
16 days ago
(429) https://twitter.com/arxiv_org/status/1038034264183304193/photo/1
Pack and Detect: Fast Object Detection in Videos Using Region-of-Interest Packing.
from twitter_favs
16 days ago
What To Tidy – Kent Beck – Medium
Some things you can tidy up in code: names, conditionals, redundancy, extraction, ordering:
from twitter_favs
17 days ago
(429) https://twitter.com/arxiv_org/status/1037787499303555072/photo/1
Developing a Purely Visual Based Obstacle Detection using Inverse Perspective Mapping.
from twitter_favs
17 days ago
[1809.01268] Developing a Purely Visual Based Obstacle Detection using Inverse Perspective Mapping
Developing a Purely Visual Based Obstacle Detection using Inverse Perspective Mapping.
from twitter_favs
17 days ago
Differential Equations Notes
A First Course in Differential Equations for Scientists and Engineers
from twitter_favs
18 days ago
Twitter
Speaking of the upcoming deadline, here is my favorite video from SysML18 from Mike Jordan, that everyone…
from twitter_favs
18 days ago
Twitter
I'm writing a 4 part drawsplainer on how browser works🎉

No CompSci degree necessary, if you've written HTML/CSS/JS…
from twitter_favs
18 days ago
Twitter
RT : "Latency Numbers Every Programmer Should Know"

It is hard for humans to get the picture until you translate it to…
from twitter_favs
18 days ago
Twitter
新的博客文章《哈希碰撞与生日攻击》:哈希碰撞的概率取决于两个因素,取值空间的大小(即哈希值的长度),以及整个生命周期中,哈希值的计算次数。

这个问题在数学上早有原型,叫做"生日问题":一个班级需要有多少人,才能保证每个同学的生日…
from twitter_favs
18 days ago
Cycle of Mathematics: The Six Handshakes – Relatively Prime
Cycle of Mathematics: A new series about how math is made, from Samuel Hansen. His first guest is
from twitter_favs
19 days ago
Twitter
Measuring context switching and memory overheads for Linux threads --
from twitter_favs
19 days ago
« earlier      
academic ad airline algorithm amazon api app apple architecture automation aws backup baidu bash benchmark bigdata biography bitcoin book business c c++ c++11 car career chrome clojure cmake cmd code compiler conference config course cpp crawler creativity credit-card cv d3.js data data-science data-structures database debug deep-learning deliberate-practice design distributed dns docker driving dropbox earphones economics editor education emacs email encode encryption engineering facebook finance focus font functional-programming game gan geometry gfw git github golang google gpu graph gtd guide habits hackernews hadoop hardware haskell hbase health ide image_processing intellij interview invest ios iptables ipython iterm java javascript jeffdean jetbrains julia jvm kaggle kent_beck keyboard knowledge latex learning leiningen library linux lisp logging lua mac machine-learning management math mathematica matplotlib matrix medicine memory method microsoft mosh mwc neovim netflix network neural-network nlp node note notebook numpy nvidia omnifocus openmp optimization org-mode osx papers parallel performance phd physics planning plugin privacy probability procrastination productivity profiling programming projects proxy psychology python pytorch quadrotor quora r reading recommender reference reinforcement-learning reproducibility research resources rnn rsync ruby rumor rust sbt scala scalability science security server service setup shell shopping shortcuts sleep software spark ssh stackoverflow startup statistics studyhacks sublime-text surge sync sysadmin system tdd tensorflow terminal test thinking time tmux tools trading travel tutorial twitter ubuntu unix unread v2ex vagrant version_control vim virtualization vision visualization vpn web wiki windows workflow writing zhihu zotero zsh

Copy this bookmark:



description:


tags: