Subject

Data Science

The Computer Vision Pipeline, Part 2: input images

From Grokking Deep Learning for Computer Vision by Mohamed Elgendy

In this part, we will discuss the input images for computer vision systems.

Computer Vision Pipeline, Part 1: the big picture

From Grokking Deep Learning for Computer Vision by Mohamed Elgendy

In this article, we’ll zoom in on the interpreting device component (of a computer vision system) to take a look at the pipeline it uses to process and understand images.

Free eBook: Exploring Deep Learning for Language

freeSmith_EDLfL

Chapters selected by Jeff Smith

Serverless AI Solutions

From AI as a Service by Peter Elger, Eoin Shanaghy, and Johannes Ahlmann

slideshare-serverless-ai-solutions

Machine Learning from the Ground up

From Machine Learning for Mortals (Mere and Otherwise) by Hefin I. Rhys

slideshare-machine-learning-from-the-ground-up

Beyond Beyond Spreadsheets

Six Questions for Jonathan Carroll, author of Beyond Spreadsheets with R

By Frances Lefkowitz

Jonathan Carroll is a data science consultant providing R programming services. He holds a PhD in theoretical physics.

Modern Data Solutions with Python

From Python for Big Datasets by John T. Wolohan

The Inner Workings of Spark

spark_in_act

From Spark in Action, Second Edition by Jean George Perrin

The Magic of Graphs and Machine Learning

PMachineLearning-MM
From Graph-Powered Machine Learning by Alessandro Negro

The Random Cut Forest Algorithm

From Machine Learning for Business by Doug Hudgeon and Richard Nichol

In this article, you’ll see how SageMaker and the Random Cut Forest algorithm can be used to create a model that will highlight the invoice lines that Brett should query with the law firm. The result will be a repeatable process that Brett can apply to every invoice that will keep the lawyers working for his bank on their toes and will save the bank hundreds of thousands of dollars per year. Off we go!

© 2019 Manning — Design Credits