​Scaling Uber’s Apache Hadoop Distributed File System for Growth

Post on how #Uber team handles #Hadoop challenges.

https://eng.uber.com/scaling-hdfs/

#BigData #HDFS

🔗 Scaling Uber’s Hadoop Distributed File System for Growth
Uber's Data Infrastructure team overhauled our approach to scaling our storage infrastructure by incorporating several new features and functionalities, including ViewFs, NameNode garbage collection tuning, and an HDFS load management service.

Naive Bayes Classifier | Naive Bayes Algorithm | Naive Bayes Classifier With Example

🎥 Naive Bayes Classifier | Naive Bayes Algorithm | Naive Bayes Classifier With Example | Simplilearn
👁 1 раз ⏳ 2625 сек.
This Naive Bayes Classifier tutorial video will introduce you to the basic concepts of Naive Bayes classifier, what is Naive Bayes and Bayes theorem, conditional probability concepts used in Bayes theorem, where is Naive Bayes classifier used, how Naive Bayes algorithm works with solved examples, advantages of Naive Bayes. By the end of this video, you will also implement Naive Bayes algorithm for text classification in Python.

The topics covered in this Naive Bayes video are as follows:

1. What is Naive

🎥 Recognize Text in Images with ML Kit on iOS (Firecasts)
👁 1 раз ⏳ 409 сек.
Lets help you apply machine learning to your iOS app. In this episode of Firecasts, Jen Person guides you through an example of how to detect, and recognize text in images using ML Kit. ML Kit beta brings Google’s machine learning expertise to mobile developers in a powerful and easy-to-use package. Find out how you can incorporate machine learning into your app with just a few lines of code! Stay tuned for the Android episode of recognizing text in images, and subscribe to the channel for more tutorials!

MIT AI: Poker and Game Theory
https://www.youtube.com/watch?v=b7bStIQovcY

🎥 MIT AI: Poker and Game Theory (Tuomas Sandholm)
👁 1 раз ⏳ 3978 сек.
Tuomas Sandholm is a professor at CMU and co-creator of Libratus, which is the first AI system to beat top human players at the game of Heads-Up No-Limit Texas Hold'em. He has published over 450 papers on game theory and machine learning, including a best paper in 2017 at NIPS / NeurIPS. His research and companies have had wide-reaching impact in the real world, especially because he and his group not only propose new ideas, but also build systems to prove these ideas work in the real world. This conversati

TensorFlow for JavaScript

🎥 TensorFlow for JavaScript (TensorFlow @ O’Reilly AI Conference, San Francisco '18)
👁 1 раз ⏳ 1982 сек.
TensorFlow.js is the recently-released JavaScript version of TensorFlow that runs in the browser and Node.js. In this talk, the team introduced the TensorFlow.js ML framework, and showed with demo on how to perform the complete machine-learning workflow, including the training, client-side deployment, and transfer learning.

Reference Links
TensorFlow.js → http://bit.ly/TF-JS
GitHub → http://bit.ly/GitHub-TFJS

More TensorFlow videos at O'Reilly AI Conference SF → http://bit.ly/2SjsvZN
Please remember to li

​How to Develop a Weighted Average Ensemble for Deep Learning Neural Networks

https://machinelearningmastery.com/weighted-average-ensemble-for-deep-learning-neural-networks/

🔗 How to Develop a Weighted Average Ensemble for Deep Learning Neural Networks
A modeling averaging ensemble combines the prediction from each model equally and often results in better performance on average than a given single model. Sometimes there are very good models that we wish to contribute more to an ensemble prediction, and perhaps less skillful models that may be useful but should contribute less to an …

​Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

New SOTA on cross-lingual transfer (XNLI, MLDoc) and bitext mining (BUCC) using a shared encoder for 93 languages.

Link: https://arxiv.org/abs/1812.10464

#SOTA #NLP

🔗 Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

​https://m.youtube.com/watch?v=U0LOSHY7U5Q

🔗

​Battling Entropy: Making Order of the Chaos in Our Lives

Article on #entropy as a concept.

Link: https://fs.blog/2018/11/entropy/

🔗 Battling Entropy: Making Order of the Chaos in Our Lives
The second law of thermodynamics says that all things move toward chaos and disorder. Our bodies, our relationships, our businesses. Are we doomed to simply accept it? Maybe not...

​Wonderfully interactive, gentle, and well done introduction to probability and statistics. Walk through this with your favorite kid and give them a head-start in life on ML

https://seeing-theory.brown.edu/basic-probability/index.html

🔗 Basic Probability
This chapter is an introduction to the basic concepts of probability theory.

🎥 Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
👁 1 раз ⏳ 2504 сек.
Talk slides @ https://qdata.github.io/secureml-web/pic/18Webnar_feature_squeezing-V2.pdf

On December 21 @ 12noon, Dr Qi gave a distinguished webinar talk in the Fall 2018 webinar series of the Institute for Information Infrastructure Protection (I3P) (@ the George Washington University and SRI International).

The recording has small issues in displaying the slides.

More relevant projects are introduced at http://www.securemachinelearning.org/

Total Least Squares in comparison with OLS and ODR
https://towardsdatascience.com/total-least-squares-in-comparison-with-ols-and-odr-f050ffc1a86a?source=collection_home---4------3---------------------

https://habr.com/company/ashmanov_net/blog/434712/

Третий Тест Тьюринга на русском языке

#machinelearning #neuralnets #deeplearning #машинноеобучение

Наш телеграмм канал - https://yangx.top/ai_machinelearning_big_data

​Applied Deep Learning with Python Use scikit-learn, TensorFlow, and Keras

📝 Applied Deep Learning with Python Use scikit-learn, TensorFlow, and Keras to create intelligent systems and machine learning... - 💾35 586 419

🎥 Can AI Pick Your Next Winning Lottery Number?
👁 2 раз ⏳ 325 сек.
AI operates based on data. We have years of lottery number data. Can we use it to pick the next number?

What are the characteristics of problems that can be solved by AI and machine learning?

​On Optimization And Expressiveness In Deep Learning By Nadav Cohen 2018

🔗 On Optimization And Expressiveness In Deep Learning By Nadav Cohen 2018
On Optimization And Expressiveness In Deep Learning By Nadav Cohen 2018 Subscribe Now!

​How to Develop a Stacking Ensemble for Deep Learning Neural Networks in Python With Keras

https://machinelearningmastery.com/stacking-ensemble-for-deep-learning-neural-networks/

🔗 How to Develop a Stacking Ensemble for Deep Learning Neural Networks in Python With Keras
Model averaging is an ensemble technique where multiple sub-models contribute equally to a combined prediction. Model averaging can be improved by weighting the contributions of each sub-model to the combined prediction by the expected performance of the submodel. This can be extended further by training an entirely new model to learn how to best combine …

Engineering Lessons Learned by Data Scientists | Data Council NYC '18

https://www.youtube.com/watch?v=Oa1t1GFVwxM

🎥 Engineering Lessons Learned by Data Scientists | Data Council NYC '18
👁 1 раз ⏳ 1842 сек.
ABOUT THE TALK:

MalwareScore is a machine learning based antivirus solution included in Endgame's enterprise security platform. It is fast, lightweight, frequently updated, and has been continually expanded to more and more file types. MalwareScore's journey from Kaggle competition code built in 2015, to brittle proof of concept, to robust production model running on customer workstations contains many twists and turns.

I'll talk about how a small team of data scientists built the original data pipeline a

Applying Statistical Modeling and Machine Learning to Perform Time-Series Forecasting

🎥 Applying Statistical Modeling and Machine Learning to Perform Time-Series Forecasting
👁 1 раз ⏳ 5106 сек.
Forecasting time-series data has applications in many fields, including finance, health, etc. There are potential pitfalls when applying classic statistical and machine learning methods to time-series problems. This talk will give folks the basic toolbox to analyze time-series data and perform forecasting using statistical and machine learning models, as well as interpret and convey the outputs.

EVENT:

PyData Los Angeles

SPEAKER:

Tamara Louie

CREDITS:

Original video source: https://www.youtube.com/wat