Sven van der Burg

Results 41 issues of Sven van der Burg

Add explanation of hyperparamter tuning to episode 3 In this section: https://carpentries-incubator.github.io/deep-learning-intro/03-monitor-the-model/index.html#counteract-model-overfitting we are actually doing hyperparamter tuning (we are changing a hyperparameter). It is only a small extra step...

Episode 3
lesson-dev-sprint

After #264 is done we should submit the lesson to Carpentries Lab.

Carpentries Lab

To give more intuition of how deep neural networks work, we could include in the introduction that you can view neural networks as learning increasingly abstract representations of the input...

nice-to-have

The picture of the confusion matrix in episode 2 does not have the 'predicted label' and 'true label' labels: https://carpentries-incubator.github.io/deep-learning-intro/2-keras.html#confusion-matrix, whereas the commands in the material actually create these labels.

good first issue
nice-to-have

See https://github.com/carpentries-incubator/deep-learning-intro/pull/277#discussion_r1036856278

nice-to-have

## Rationale Quickly show that using a GPU for training a network is both easy and speeds up training significantly. ## Learning objectives * Use a GPU when training a...

status:out of scope

@anenadic, @bielsnohr, @steve-crouch We (me and some colleagues from the Netherlands eScience Center) are planning to add some improvements to this lesson in a lesson development sprint day at the...

sprint

### As a fast learner I want to have optional exercises/assignments at the end of each section. When teaching this lesson in person (#159), we notice that some participants already...

Hey, We recently taught a workshop using this material see https://github.com/carpentries-incubator/python-intermediate-development/issues/159 . We organized an additional morning on continuous integration/continuous deployment. We added the section to the material in our...

At the [Netherlands eScience Center](https://www.esciencecenter.nl/) we have taught quite a similar machine learning lesson a few times now. The material that we use works quite well so we are progressing...