Spark is known as a fast general-purpose cluster-computing framework for processing big data. In this post, we’re going to cover how Spark works under the hood and the things you need to know to be able to effectively perform distributing machine learning using PySpark. The post assumes basic familiarity with Python and the concepts of machine learning like regression, gradient descent, etc.
As industries shift to a microservices approach of deploying applications using containers, data scientists can reap the benefits. Data Scientists use specific frameworks and operating systems that can often conflict with the requirements of a production system. This has led to many clashes between IT and R&D departments. IT is not going to change the OS to meet the needs of a model that needs a specific framework that won’t run on RHEL 7.2.
A common sentiment among our prospects after they see our demo for the first time is: “That’s it? It can’t be that simple!”. The truth is – yes it can be, and it should be. ML and AI should make IT Ops simpler, and a big part of that is usability. If your ML & AI powered IT Ops tools take months to set up and weeks to learn, and then don’t provide a substantially improved user experience, you’re obviously using the wrong tools.
This post demonstrates a *basic* example of how to build a deep learning model with Keras, serve it as REST API with Flask, and deploy it using Docker and Kubernetes. This is NOT a robust, production example. This is a quick guide for anyone out there who has heard about Kubernetes but hasn’t tried it out yet. To that end, I use Google Cloud for every step of this process.
Five worthy reads is a regular column on five noteworthy items we’ve discovered while researching trending and timeless topics. This week, we’ll talk about why incorporating AI into your UEM strategy may be inevitable.
