The applications of machine learning are seemingly endless (as Juan De Dios Santos demonstrates, building a pikachu detection app). But whilst an increasing number of data scientists are familiarising themselves with the technology, finding successful use cases that are scaled and robust is still difficult.
This is, at least in part, due to the fact that building an accurate and unbiased model can barely considered to be half the battle. Other people need to use it! As Ian Xiao discusses in another of our Edition articles, even if you can get the model out into the world there are interaction, execution and feedback problems that lie in wait to disrupt your AI aspirations… Our picks for this month are here to help you pick the right stack for releasing your model, properly.
Joshua Fleming – Editorial Associate
Deploying a Machine Learning Model as a REST API
By Nguyen Ngo – 6 min read
As a Python developer and data scientist, I have a desire to build web apps to showcase my work. As much as I like to design the front-end, it becomes very overwhelming to take both machine learning and app development.
Deploying a Keras Deep Learning Model as a Web Application in Python
By Will Koehrsen – 7 min read
Deep learning, web apps, Flask, HTML, and CSS in one project
Deploying deep learning models
By Isaac Godfried – 5 min read
Recently, academic and industry researchers have conducted a lot of exciting and ground-breaking research in the field of deep learning.
Deploying Keras models using TensorFlow Serving and Flask
By Himanshu Rawlani – 8 min read
Often there’s a need to abstract away your machine learning model details and just deploy or integrate it with easy to use API endpoints.
Detecting Pikachu on Android using Tensorflow Object Detection
By Juan De Dios Santos – 12 min read
Deep inside the many functionalities and tools of TensorFlow, lies a component named TensorFlow Object Detection API.
Fixing the Last Mile Problems of Deploying AI Systems in the Real World
By Ian Xiao – 10 min read
Last mile problems are the final hurdles to realizing AI’s promised values.
Deploying Keras Deep Learning Models with Flask
By Ben Weber – 7 min read
This post demonstrates how to set up an endpoint to serve predictions using a deep learning model built with Keras.
Deploying scikit-learn Models at Scale
By Yufeng G – 4 min read
Scikit-learn is great for putting together a quick model to test out your dataset. But what if you want to run it against incoming live data?
We also thank all the great new writers who joined us recently, Michael Boles, Akash Tandon, Yves Peirsman, Jan Van Zeghbroeck, Andrew E Brereton, Viviane Lindenbergh, Simon Hellemann Flachs, Nikolai Liubimov, Serafim Batzoglou, Damian Draxler, Fatos Morina, Dmitry Borisenko, Mason McGough, Richard Liaw, Jahangir Mammadov, Boris Knyazev, Shor Joel, Daniel Hogan, Alex Muhr, Andy Patterson, SJ Porter, and many others. We invite you to take a look at their profiles and check out their work.
