Digital-Thinking
A blog about machine learning and software development
Preprocessing and data transformation are the most important parts of all machine learning pipelines. No matter what type of model you use, if the preprocessing sucks, your model sucks too. This remains also true, if you are dealing with deep…
In this How-To series, I want to share my experience with machine learning models in productions environments. This starts with the general differences to typical software projects and how to acquire and deal with data sets in such projects, goes…
Besides computer vision, artificial neural networks (ANNs) are also very popular in natural language processing. Automatic translation or sentiment analysis of reviews are well known areas, where (recurrent) neural networks are used a lot. Around natural language understanding, there are…
Just about one year ago, I was trying to make the distinction between data science and data engineering. But in the past year a new job role has become very popular (at least I noticed it in job postings and…
In this post I will show how to combine features from natural language processing with traditional features (meta data) in one single model in keras (end-to-end learning). This can be done, by using multiple inputs models. Problem definition In applied…
In this post I want to show you a very nice technology stack, which can be used to manage your passwords in Keepass, connect it to your web browser and make it possible to open ssh and scp connections easily….
In this post I will show, how to report jmx metrics to logstash via TCP on a push based way, without changing java code from an existing application.
Data engineering is the link between data science and software engineering. Data engineers often work together with data scientists and analysts and help them to do their job efficiently. Moreover they are responsible for transforming models and prototypes built by…
In the last months I was working on a deep learning project. The goal was to dig into Tensorflow and deep learning in gerneral. For this purpose I re-implemented a paper from January 2016 called convolutional pose machines , which uses deep…