Free workshop on Deep Learning with Keras and TensorFlow

The Good, the Bad and the Ugly: how (not) to visualize data

Oct 10, 2020

This is the complete code used to create the ggplot2 graphs in my talk The Good, the Bad and the Ugly: how (not) to visualize data at this year’s data2day conference. You can find the slides here. If you have questions or would like to talk about this article (or something else data-related), you can now book 15-minute timeslots with me (it’s free - one slot available per weekday): If you have been enjoying my content and would like to help me be able to create more, please consider sending me a donation at paypal.

Using Keras Callbacks

Sep 9, 2020

This is article #3 in my recent series on how to get the most out of Keras. The two other articles are: Update with TF 2.0: Image classification with Keras and TensorFlow Whose dream is this? When and how to use the Keras Functional API Keras comes with a number of built in callbacks. Callbacks are useful for optimizing/customizing your training runs and are used with the fit() function. Here, I’ll show which callbacks come built into Keras and how to write your own custom callbacks.

Free workshop on Deep Learning with Keras and TensorFlow

Sep 9, 2020

Workshop announcement Because this year’s UseR 2020 in Munich couldn’t happen as an in-person event, I will be giving my workshop on Deep Learning with Keras and TensorFlow as an online event on Thursday, 8th of October (13:00 UTC / 15:00 CEST) You can register for FREE via Eventbrite. Deep learning is an artificial intelligence that mimics the workings of a human brain in processing different data, creating patterns and interpreting information that is used for decision making.

Whose dream is this? When and how to use the Keras Functional API

Sep 9, 2020

I have been working with Keras for a while now, and I’ve also been writing quite a few blogposts about it; the most recent one being an update to image classification using TF 2.0. However, in my blogposts I have always been using Keras sequential models and never shown how to use the Functional API. The reason is that the Functional API is usually applied when building more complex models, like multi-input or multi-output models.

Update with TF 2.0: Image classification with Keras and TensorFlow

Sep 9, 2020

Recently, I have been getting a few comments on my old article on image classification with Keras, saying that they are getting errors with the code. And I have also gotten a few questions about how to use a Keras model to predict on new images (of different size). Instead of replying to them all individually, I decided to write this updated version using recent Keras and TensorFlow versions (all package versions and system information can be found at the bottom of this article, as usual).

Baby Weight Shiny app

Sep 9, 2020

Alright, this is it: I am officially back! :-D I have not written any blogposts for over a year. Last year, I had the cutest baby boy and ever since then, I did not get around to doing much coding. One of the reasons was that, unfortunately, we did not have the easiest of starts with the little one. Feeding problems led to weight gain problems, so we had to weigh him regularly.

Word2Vec Text Mining & Parallelization in R. Join MünsteR for our next meetup!

Jun 6, 2019

In our next MünsteR R-user group meetup on Tuesday, July 9th, 2019, we will have two exciting talks about Word2Vec Text Mining & Parallelization in R! You can RSVP here: https://www.meetup.com/de-DE/Munster-R-Users-Group/events/262236134/ Thorben Hellweg will talk about Parallelization in R. More information tba! Maren Reuter from viadee AG will give an introduction into the functionality and use of the Word2Vec algorithm in R. Text data in its raw form cannot be used as input for machine learning algorithms.

Before you take my DataCamp course please consider this info

Apr 4, 2019

Today, I am finally getting around to writing this very sad blog post: Before you take my DataCamp course please consider the following information about the sexual harassment scandal surrounding DataCamp! UPDATE from April 26th: Yesterday, DataCamp’s CEO Jonathan Cornelissen issued an apology statement and the DataCamp Board of Directors wrote an update about the situation and next steps (albeit somewhat vague) they are planning to take in order to address the situation.

Upcoming talks in spring 2019

Mar 3, 2019

This spring, I’ll be giving talks at a couple of Meetups and conferences: March, 26th: At the data lounge Bremen, I’ll be talking about Explainable Machine Learning April, 11th: At the Data Science Meetup Bielefeld, I’ll be talking about Building Interpretable Neural Networks with Keras and LIME May, 14th: At the M3 conference in Mannheim, a colleague and I will give our workshop on building production-ready machine learning models with Keras, Luigi, DVC and TensorFlow Serving

Getting started with RMarkdown & trying to make it in the world of Kaggle. Join MünsteR for our next meetup!

Mar 3, 2019

In our next MünsteR R-user group meetup on Tuesday, April 9th, 2019, we will have two exciting talks: Getting started with RMarkdown and Trying to make it in the world of Kaggle! You can RSVP here: http://meetu.ps/e/Gg5th/w54bW/f Getting started with RMarkdown First, Niklas Wulms from the University Hospital, Münster will give an introduction to RMarkdown: He started using R in 2018 and learnt the advantages of using only one framework of free software and code.

Free workshop on Deep Learning with Keras and TensorFlow

Workshop announcement

Dr. Shirin Elsinghorst

The Good, the Bad and the Ugly: how (not) to visualize data

Using Keras Callbacks

Free workshop on Deep Learning with Keras and TensorFlow

Whose dream is this? When and how to use the Keras Functional API

Update with TF 2.0: Image classification with Keras and TensorFlow

Baby Weight Shiny app

Word2Vec Text Mining & Parallelization in R. Join MünsteR for our next meetup!

Before you take my DataCamp course please consider this info

Upcoming talks in spring 2019

Getting started with RMarkdown & trying to make it in the world of Kaggle. Join MünsteR for our next meetup!