Skip to content

ML in Production

Best practices for building real world machine learning systems

  • Newsletter
  • Courses
    • Build, Deploy, and Monitor ML with Amazon SageMaker
  • About

Category: Deployment

Kubernetes Services for Machine Learning

Kubernetes Services for Machine Learning
In my previous Kubernetes for Machine Learning post, we used a Kubernetes Deployment to build a REST API to serve a trained machine learning model. In that setup, issuing requests to generate predictions was only possible from within our Kubernetes… Read More
Author LuigiPosted on June 24, 2019June 23, 2019Categories Deployment, Inference, KubernetesLeave a comment on Kubernetes Services for Machine Learning

The Ultimate Guide to Model Retraining

The Ultimate Guide to Model Retraining
Machine learning models are trained by learning a mapping between a set of input features and an output target. Typically, this mapping is learned by optimizing some cost function to minimize prediction error. Once the optimal model is found, it’s… Read More
Author LuigiPosted on June 10, 2019March 21, 2020Categories DeploymentTags Monitoring, Retraining1 Comment on The Ultimate Guide to Model Retraining

Kubernetes Deployments for Machine Learning

Kubernetes Deployments for Machine Learning
Suppose your data science team has deployed a couple of batch machine learning processes on Kubernetes. You’ve successfully used Kubernetes Jobs to deploy model training and you’ve scheduled daily batch inference tasks using CronJobs. But now you’re tasked with serving… Read More
Author LuigiPosted on June 3, 2019June 2, 2019Categories Deployment, Inference, KubernetesLeave a comment on Kubernetes Deployments for Machine Learning

Kubernetes CronJobs for Machine Learning

Kubernetes CronJobs for Machine Learning
In my previous post we discussed how to leverage Kubernetes Jobs to perform common production machine learning tasks such as model training and batch inference. Jobs allow us to reliably run batch processes in a fault tolerant way. Even if… Read More
Author LuigiPosted on May 27, 2019May 25, 2019Categories Deployment, KubernetesLeave a comment on Kubernetes CronJobs for Machine Learning

Kubernetes Jobs for Machine Learning

Kubernetes Jobs for Machine Learning
In my previous post I introduced Kubernetes Pods, the basic building block of the Kubernetes ecosystem. In that post I discussed what a Pod is, how it fits into the Kubernetes system, and how to create, view, and delete a… Read More
Author LuigiPosted on May 20, 2019May 19, 2019Categories Deployment, Inference, Kubernetes, TrainingLeave a comment on Kubernetes Jobs for Machine Learning

Using Docker to Generate Machine Learning Predictions in Real Time

Figure 1. A REST API serves as the communication layer between a machine learning model and incoming data. Introduction In Part III of our Docker for Machine Learning series, we learned how to use Docker to perform model training and… Read More
Author LuigiPosted on April 1, 2019March 23, 2020Categories Deployment, Docker, Inference5 Comments on Using Docker to Generate Machine Learning Predictions in Real Time

Batch Inference vs Online Inference

Introduction You’ve spent the last few weeks training a new machine learning model. After working with the product team to define the business objectives, translating these objectives into appropriate evaluation metrics, and several rounds of iterative feature engineering, you’re ready… Read More
Author LuigiPosted on March 25, 2019May 30, 2022Categories Deployment, Inference1 Comment on Batch Inference vs Online Inference

Posts pagination

Previous page Page 1 Page 2

Mission

My goal is to help data scientists, ML engineers, and AI product managers, build and operate machine learning systems in production.

Learn more about why I started MLinProduction.

Enroll in my online course

Sagemaker Course Banner

Recent Posts

  • Driving Experimentation Forward through a Working Group (Experimentation Program Series: Guide 03)
  • What is an Experimentation program and Who is Involved? (Experimentation Program Series: Guide 02)
  • Building An Effective Experimentation Program (Experimentation Program Series: Guide 01)
  • Lessons Learned from Writing Online
  • Newsletter #087
  • Newsletter
  • Courses
    • Build, Deploy, and Monitor ML with Amazon SageMaker
  • About
ML in Production Disclaimer