2021 for sure was one of the most exciting, challenging, and rewarding years of my career so far. Like last year, I’ve decided to kickstart this year with a short review of 2021 and give an outlook on what’s on the menu for 2022. Spoiler alert: This year is already casting large shadows for us – due to the rise of statworx next.
Recap: 5 Highlights from the Digital Festival Zurich 2021
After participating in the Digital Festival for the first time last year, the whole Swiss team of STATWORX was looking forward to this year’s edition, which took place from September 23 to 26 in Zurich at Schiffbau, located conveniently just around the corner of our Swiss office. Under the motto «Make It Personal», a variety of keynotes, labs and networking sessions brought together digital leaders, digital aficionados and innovators, all driven by curiosity, openness and a maker mentality. In keeping with this year’s Digital Festival motto, I would like to share my personal five highlights of this recent event with you now.
Why Data Science and AI Initiatives Fail – A Reflection on Non-Technical Factors
In this article, Lea Waniek (Data & Strategy Consultant) highlights the top 4 (non-technical) reasons for the failure of DS & AI initiatives. To counteract the pitfalls she identifies, she presents several possible solutions to each issue.
How to Automatically Create Project Graphs With Call Graph
Your project’s codebase keeps growing and it daunts you. We’ve all been there. Maybe this tool can help you. Felix Plagge has written a package that creates a call graph for any Python script. In this article, he first explains what project graphs are useful for and then explains the installation and usage of his package called project_graph.
STATWORX Cheatsheets – Python Basics Cheatsheet for Data Science
Do you want to learn Python? Or maybe you need a little reminder from time to time while coding? That’s exactly why cheatsheets were invented! Our first cheatsheet with Python basics is the start of a new blog series, where more cheatsheets will follow in our unique STATWORX style.
Deploy and Scale Machine Learning Models with Kubernetes
In this article, Jonas Braun reports on the most common way to use Kubernetes: with cloud providers like Google GCP, Amazon AWS or Microsoft Azure. In the article, he looks at how to deploy these containers (i.e. applications or models) reliably and scalably for customers, other applications, internal services or computations with Kubernetes. Finally, the article gives an outlook on tools and further developments.
3 Scenarios for Deploying Machine Learning Workflows Using MLflow
Deploying and monitoring machine learning projects is a complex undertaking. In this article, John Vicente presents the typical challenges along the machine learning workflow and describes a possible solution platform with MLflow. In addition, we present three different scenarios that can be used to professionalize machine learning workflows.
Car Model Classification IV: Integrating Deep Learning Models with Dash
Did you want to know how to build a web frontend in Python? In the 4th and last part of our blog series, we develop an interactive game. The user has to guess the car brand and model. Do you think you can beat our AI?
Car Model Classification III: Explainability of Deep Learning Models with Grad-CAM
In the third part of our blog series, we cover an essential topic that has gained significant traction in the ML-community in the past years: Explainability. Explainable AI is essential to establish trust in the models we develop. We discuss various approaches for CNN networks, with a particular focus on the Grad-CAM method.
Car Model Classification II: Deploying TensorFlow Models in Docker using TensorFlow Serving
How do we interact with machine learning models in practice? In the second part of our 4-part blog series on car model classification, you will learn how models can be deployed using TensorFlow Serving, and how we can run model queries.