Adding links to Maths, Cloud and ML, DL and main sections of Julia, P…

…ython, R
jasmcole · Jun 19, 2020 · 818297b · 818297b
1 parent d21953d
commit 818297b
Show file tree

Hide file tree

Showing 5 changed files with 22 additions and 3 deletions.
diff --git a/cloud-devops-infra/README.md b/cloud-devops-infra/README.md
@@ -57,7 +57,7 @@ reproducible research
   - [Nextflow](https://www.nextflow.io/) - Data-driven computational pipelines. Nextflow enables scalable and reproducible scientific workflows using software containers. It allows the adaptation of pipelines written in the most common scripting languages.
   - [StackHPC suites of repositories: AI, ML, DL, Cloud, HPC](https://github.com/stackhpc) | [StackHPC](http://stackhpc.com/)
   - [cortex](https://www.cortex.dev/) - Machine learning deployment platform: Deploy machine learning models to production
-  - [#Uber introduces #Fiber, an #AI development and distributed training platform for methods including reinforcement learning and population-based learning.](https://www.linkedin.com/posts/inna-vogel-nlp_introduction-to-fiber-activity-6649564159828606976-Jmi6) 
+  - [#Uber introduces #Fiber, an #AI development and distributed training platform for methods including reinforcement learning and population-based learning.](https://www.linkedin.com/posts/inna-vogel-nlp_introduction-to-fiber-activity-6649564159828606976-Jmi6)| [Uber Open-Sources Fiber - A New Library For Distributed Machine Learning](https://www.linkedin.com/posts/eric-feuilleaubois-ph-d-43ab0925_uber-open-sources-fiber-a-new-library-for-activity-6656446088502923264-Dnv-)
   - [A curated list of awesome pipeline toolkits inspired by Awesome Sysadmin](https://github.com/pditommaso/awesome-pipeline)
   - [H2O Framework for Machine Learning](https://www.linkedin.com/posts/data-science-central_h2o-framework-for-machine-learning-activity-6635175109445382144-ISgt)
   - [ML Framework: Introducing Ludwig, a Code-Free Deep Learning Toolbox](https://eng.uber.com/introducing-ludwig/) | [Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code](https://github.com/uber/ludwig)

diff --git a/details/julia-python-and-r.md b/details/julia-python-and-r.md
@@ -73,6 +73,8 @@
   - [Neural Networks are Function Approximation Algorithms](https://machinelearningmastery.com/neural-networks-are-function-approximators/)
   - [Troubleshooting Deep NNs](http://josh-tobin.com/assets/pdf/troubleshooting-deep-neural-networks-01-19.pdf)
   - [Understand the Impact of Learning Rate on Neural Network Performance](https://machinelearningmastery.com/understand-the-dynamics-of-learning-rate-on-deep-learning-neural-networks/)
+  - [Andrej Karpathy’s blog post: Neural Network recipes](http://karpathy.github.io/2019/04/25/recipe/)
+  - [Spektral is a Python library for graph deep learning, based on the Keras API and TensorFlow 2](https://github.com/danielegrattarola/spektral/)
 
   ## Generative Adversarial Network (GAN)
 
@@ -173,6 +175,8 @@
   - [Data Science In One Pictures](https://www.linkedin.com/posts/nabihbawazir_artificialintelligence-facialrecognition-activity-6611503084294234112-eH0K)
   - [Data Science complete PDF](https://sites.google.com/view/data-science-complete-pdf/home?fbclid=IwAR0ftE_DavpoCUJ77ipkxNHydUhZw_yYw5tNo6xjbce50Ge-XYRjAz67Tj8)
   - [Data Science Cheatsheet](https://www.linkedin.com/posts/data-science-central_machine-learning-and-data-science-cheat-sheet-activity-6623699004276428800-DYcb)
+  - [FREE #AI/ #DataScience/ #MachineLearning CHEAT SHEETS courtesy of Stanford University!](https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-machine-learning-tips-and-tricks)
+  - [All in One Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data](https://www.linkedin.com/posts/iamsivab_cheat-sheets-for-ai-neural-networks-activity-6655792426420142080-4QlD)
   - [Data Science Lifecycle](https://www.linkedin.com/posts/nabihbawazir_data-science-lifecycle-activity-6606559313404227584-XyIi)
   - [50 most popular Python libraries and frameworks used in data science](https://www.linkedin.com/posts/nabihbawazir_python-datascience-dataanalysis-activity-6604589510447722496-AvyE)
   - [Data Science Process by Nabih Bawazir](https://www.linkedin.com/posts/nabihbawazir_datascience-machinelearning-activity-6607204688909701120-9RqN)

diff --git a/details/julia-python-and-r/machine-learning.md b/details/julia-python-and-r/machine-learning.md
@@ -52,7 +52,7 @@
   - [A-Z Machine Learning Resources](https://lnkd.in/fVqeSfk)
   - [𝗣𝘆𝘁𝗵𝗼𝗻 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗣𝗿𝗼𝗷𝗲𝗰𝘁𝘀](https://www.linkedin.com/posts/martinroberts_python-machine-learning-projects-activity-6620692910499295232-B8Gq)
   - [Machine Learning Map](https://www.linkedin.com/posts/nabihbawazir_machine-learning-map-activity-6604287294356713472-Zdrk)
-  - [Machine Learning Mindmap](https://www.linkedin.com/posts/nabihbawazir_datascience-machinelearning-artificialintellegence-activity-6620949255924346881-QMmy)
+  - Machine Learning Mindmap: [1](https://www.linkedin.com/posts/nabihbawazir_datascience-machinelearning-artificialintellegence-activity-6620949255924346881-QMmy) | [2](https://www.linkedin.com/posts/nabihbawazir_statistics-data-datascience-activity-6674203172506087425-IIFe)
   - [Machine Learning from scratch!](https://www.linkedin.com/posts/montrealai_artificialintelligence-deeplearning-neuralnetworks-activity-6622205152554213376-TkTs)
   - [Machine Learning in Oracle Database](https://blogs.oracle.com/machinelearning/machine-learning-in-oracle-database)
   - [34 External Machine Learning Resources and Related Articles](https://www.linkedin.com/posts/data-science-central_34-external-machine-learning-resources-and-activity-6621826667289591808-0EZP)
@@ -89,6 +89,9 @@
   - [Survival Analysis in R](https://www.geeksforgeeks.org/survival-analysis-in-r/)
   - [How to Reduce Overfitting Using Weight Constraints in Keras](https://machinelearningmastery.com/how-to-reduce-overfitting-in-deep-neural-networks-with-weight-constraints-in-keras/)
   - [How to Configure XGBoost for Imbalanced Classification](https://machinelearningmastery.com/xgboost-for-imbalanced-classification)
+  - Approaching (almost) Any Machine Learning Problem | by Abhishek Thakur | Kaggle Days Dubai | Kaggle: [original post](https://www.linkedin.com/pulse/approaching-almost-any-machine-learning-problem-abhishek-thakur) | [Video](https://www.youtube.com/watch?v=uWVR_axaVwk) | [Slides](https://www.slideshare.net/abhishekkrthakur/approaching-almost-any-machine-learning-problem-kaggledays-dubai) - highly recommended
+  - [Prediction Intervals for Machine Learning](https://machinelearningmastery.com/prediction-intervals-for-machine-learning/)
+  - [🔥The things that are changing in an experiment are called 𝙑𝘼𝙍𝙄𝘼𝘽𝙇𝙀𝙎.](https://www.linkedin.com/posts/ashishpatel2604_artificialintelligence-machinelearning-bigdata-activity-6660947977479303168-nutF)
   - Algorithms
     - See [Machine Learning algorithms](./machine-learning-algorithms.md)
   - See [Machine Learning](../courses.md#machine-learning) in [Courses](../courses.md#courses)
@@ -101,9 +104,11 @@
 - [Stack your ML models using an ensemble library: picknmix](https://github.com/picknmix/picknmix) by [Cheuk Ting Ho](https://github.com/Cheukting)
 - [PYCARET 1.0.0 - A simple, fast and efficient way to do machine learning in Python](https://www.linkedin.com/posts/montrealai_datascience-machinelearning-artificialintelligence-activity-6655244720467439616-OqVQ)
 - [Hummingbird - python library that compiles trained ML models into tensor computation for faster inference. Supported models include sklearn decision trees, random forest, lightgbm, xgboost](https://www.linkedin.com/posts/sudalairajkumar_machinelearning-activity-6676336916499181568-N0Z3)
+- [Scikit-Lego v.0.4.4](https://www.linkedin.com/posts/vincentwarmerdam_scikit-lego-v044-is-out-now-we-now-support-activity-6670949973439336448-Dhds)
 - [Huawei’s MindSpore: A new competitor for TensorFlow and PyTorch?](https://towardsdatascience.com/huaweis-mindspore-a-new-competitor-for-tensorflow-and-pytorch-d319deff2aec)
 - Hermione ML: [pypi](https://pypi.org/project/hermione-ml/) | [GitHub](https://github.com/A3Data/hermione)
 - Speed ML: [github](https://github.com/Speedml/speedml) | [Notebook](https://github.com/Speedml/notebooks/blob/master/titanic/titanic-solution-using-speedml.ipynb)
+- Embedded Learning Library: [HomePage](https://microsoft.github.io/ELL) | [GitHub](https://github.com/Microsoft/ELL)
 
 ## Metrics
 

diff --git a/details/machine-learning-algorithms.md b/details/machine-learning-algorithms.md
@@ -31,6 +31,16 @@
 - [Sparse Forest with FIL](https://www.linkedin.com/posts/miguelusque_sparse-forests-with-fil-activity-6628874338785337344-89hf)
 - [Google T5 Explores the Limits of Transfer Learning](https://www.linkedin.com/posts/eric-feuilleaubois-ph-d-43ab0925_google-t5-explores-the-limits-of-transfer-activity-6631788661920804864-wH9d)
 - [🉐 𝘈𝘋𝘝𝘈𝘕𝘛𝘈𝘎𝘌𝘚 𝘈𝘕𝘋 🉐𝘗𝘐𝘛𝘍𝘈𝘓𝘓𝘚 𝘖𝘍 𝘋𝘐𝘍𝘍𝘌𝘙𝘌𝘕𝘛 𝘈𝘓𝘎𝘖𝘙𝘐𝘛𝘏𝘔𝘚](https://www.linkedin.com/posts/ashishpatel2604_datascience-deeplearning-machinelearning-activity-6668792791658852352-87Po)
+- [One-Class Classification Algorithms for Imbalanced Datasets](https://machinelearningmastery.com/one-class-classification-algorithms/)
+- [XGboost related discussion](https://twitter.com/a_erdem4/status/1265176369731944448)
+- [Estimate the Number of Experiment Repeats for Stochastic Machine Learning Algorithms](https://machinelearningmastery.com/estimate-number-experiment-repeats-stochastic-machine-learning-algorithms/)
+- [Top Machine Learning Algorithm](https://www.linkedin.com/posts/nabihbawazir_datascience-machinelearning-artificialintellegence-activity-6656808477152907264-JAwa)
+- [14 Different Types of Learning in Machine Learning](https://machinelearningmastery.com/types-of-learning-in-machine-learning/)
+- [6 Easy Steps to Learn Naive Bayes Algorithm (with code in Python)](https://twitter.com/analyticbridge/status/1261772163289354241)
+- [Intuitively, How Can We (Better) Understand Logistic Regression by Angela Shi](https://www.linkedin.com/posts/towards-data-science_intuitively-how-can-we-better-understand-activity-6660097072131379200-m7s3)
+- [How to Develop Multi-Output Regression Models with Python](https://machinelearningmastery.com/multi-output-regression-models-with-python/)
+- [A Gentle Introduction to Cross-Entropy for Machine Learning](https://machinelearningmastery.com/cross-entropy-for-machine-learning/)
+- [How to Calculate Correlation Between Variables in Python](https://machinelearningmastery.com/how-to-use-correlation-to-understand-the-relationship-between-variables/)
 
 # Contributing
 

diff --git a/details/maths-stats-probability.md b/details/maths-stats-probability.md
@@ -148,7 +148,7 @@
 - [Develop an Intuition for Bayes Theorem With Worked Examples](https://machinelearningmastery.com/intuition-for-bayes-theorem-with-worked-examples/)
 - [Bayesian Stats 101 for Data Scientists](https://www.linkedin.com/posts/towards-data-science_bayesian-stats-101-for-data-scientists-activity-6655949045678387202-qlgP)
 - [New Marketing Insight from Unsupervised Bayesian Belief Networks](https://www.linkedin.com/posts/vincentg_new-marketing-insight-from-unsupervised-bayesian-activity-6657419179529949184-nyP4)
-
+- [Everything you need to know about Gaussian Distribution](https://deepai.org/machine-learning-glossary-and-terms/gaussian-distribution)
 
 # Contributing