Modeling “Unknown Unknowns” with TensorFlow Probability — Industrial AI, Part 3

From: https://medium.com/tensorflow/modeling-unknown-unknowns-with-tensorflow-probability-industrial-ai-part-3-52146cd0201a Posted by Venkatesh Rajagopalan, Director Data Science & Analytics; Mahadevan Balasubramaniam, Principal Data Scientist; and Arun Subramaniyan, VP Data Science & Analytics at BHGE Digital We believe in a slightly modified version of George Box’s famous comment: “All models are wrong, some are useful” for a short period of time. Irrespective of how sophisticated a model … Continue reading Modeling “Unknown Unknowns” with TensorFlow Probability — Industrial AI, Part 3 →

Predicting Known Unknowns with TensorFlow Probability — Industrial AI, Part 2

From: https://medium.com/tensorflow/predicting-known-unknowns-with-tensorflow-probability-industrial-ai-part-2-2fbd3522ebda Posted by Venkatesh Rajagopalan, Director Data Science & Analytics and Arun Subramaniyan, VP Data Science & Analytics at BHGE Digital In the first blog of this series, we presented our analytics philosophy of combining domain knowledge, probabilistic methods, traditional machine learning (ML) and deep learning techniques to solve some of the hardest problems in the industrial world. … Continue reading Predicting Known Unknowns with TensorFlow Probability — Industrial AI, Part 2 →

Industrial AI: BHGE’s Physics-based, Probabilistic Deep Learning Using TensorFlow Probability — Part 1

From: https://medium.com/tensorflow/industrial-ai-bhges-physics-based-probabilistic-deep-learning-using-tensorflow-probability-5f215c791863 By Arun Subramaniyan, VP Data Science & Analytics at BHGE Digital Baker Hughes, a GE Company (BHGE), is the world’s leading fullstream oil and gas company with a mission to find better ways to deliver energy to the world. The BHGE Digital team develops enterprise grade, AI-driven, SaaS solutions to improve efficiency and reduce non-productive time … Continue reading Industrial AI: BHGE’s Physics-based, Probabilistic Deep Learning Using TensorFlow Probability — Part 1 →

A Primer on Deep Learning in Genomics

From: https://colab.research.google.com/drive/17E4h5aAOioh5DiTo7MZg4hpL6Z_0FyWr#scrollTo=eiiwjw4yhX0P Deep Learning in Genomics Primer (Tutorial) This tutorial is a supplement to the manuscript, A Primer on Deep Learning in Genomics (Nature Genetics, 2018) by James Zou, Mikael Huss, Abubakar Abid, Pejman Mohammadi, Ali Torkamani & Amalio Telentil. Read the accompanying paper here. Paper: https://drive.google.com/file/d/1441g10nACGWVfMeMU4aYxaODYC_bl2Oi/view?usp=sharing If you have any questions or feedback regarding this tutorial, please … Continue reading A Primer on Deep Learning in Genomics →

Breast cancer classification with Keras and Deep Learning

From: https://www.pyimagesearch.com/2019/02/18/breast-cancer-classification-with-keras-and-deep-learning/ In this tutorial, you will learn how to train a Keras deep learning model to predict breast cancer in breast histology images. Back 2012-2013 I was working for the National Institutes of Health (NIH) and the National Cancer Institute (NCI) to develop a suite of image processing and machine learning algorithms to automatically analyze … Continue reading Breast cancer classification with Keras and Deep Learning →

Mastering Fast Gradient Boosting on Google Colaboratory with free GPU

On the photo NVIDIA K80 GPU, https://www.nvidia.com/ru-ru/data-center/tesla-k80/ Gradient Boosting on Decision Trees (GBDT) is a state-of-the-art Machine Learning tool for working with heterogeneous or structured data. When working with data, the choice of the perfect algorithm depends highly on the type of data. For homogeneous data, like images, sound or text, the best solution is neural networks. … Continue reading Mastering Fast Gradient Boosting on Google Colaboratory with free GPU →

Build a live dashboard with Python

From: https://pusher.com/tutorials/live-dashboard-python You will need Python 3+ installed on your machine. A basic knowledge of Python and Flask will be helpful. Introduction In the past, if we needed to build a web platform that keeps track of user actions and displays updates accordingly, say on the admin dashboard, we will have to refresh the dashboard … Continue reading Build a live dashboard with Python →

Create a Python powered dashboard in under 10 minutes

From: https://moderndata.plot.ly/create-a-plotly-dashboards-in-under-10-minutes/ Plotly graphs can be embedded in web sites to create interactive, highly customized dashboards that have many advantages over what is available with expensive, traditional BI software. Many of the world’s leading data driven companies (Netflix, Google, Siemens, and others) are using Plotly to power their dashboards. This article shows you how to create a simple Plotly dashboard using … Continue reading Create a Python powered dashboard in under 10 minutes →

Pandas for Football Analysis

A Merging and Scraping DataFrame Example using Football League Data From: https://towardsdatascience.com/pandas-for-football-analysis-42c23b252995 Introduction This tutorial will centre on how to merge DataFrames scraped from different online sources. To begin, I will merge the Premier League Table, available from, Wikipedia, with statistics relating to the average time a team spends leading, level or trailing over the course of … Continue reading Pandas for Football Analysis →