diff --git a/jose.00307/10.21105.jose.00307.crossref.xml b/jose.00307/10.21105.jose.00307.crossref.xml new file mode 100644 index 0000000..a35a716 --- /dev/null +++ b/jose.00307/10.21105.jose.00307.crossref.xml @@ -0,0 +1,344 @@ + + + + 20251019183650-7a63e4a44161abcf603fe656021e57a7a0ed40a0 + 20251019183650 + + JOSS Admin + admin@theoj.org + + The Open Journal + + + + + Journal of Open Source Education + JOSE + 2577-3569 + + 10.21105/jose + https://jose.theoj.org + + + + + 10 + 2025 + + + 8 + + 92 + + + + Introduction to deep learning: Carpentries-style hands-on lesson material for introducing researchers to deep learning + + + + Sven A. + van der Burg + + Netherlands eScience Center, Amsterdam, The Netherlands + + https://orcid.org/0000-0003-1250-6968 + + + Pranav + Chandramouli + + Netherlands eScience Center, Amsterdam, The Netherlands + + https://orcid.org/0000-0002-7896-2969 + + + Anne + Fouilloux + + Simula Research Laboratory, Oslo, Norway + + https://orcid.org/0000-0002-1784-2920 + + + Cunliang + Geng + + Netherlands eScience Center, Amsterdam, The Netherlands + + https://orcid.org/0000-0002-1409-8358 + + + Toby + Hodges + + The Carpentries, USA + + https://orcid.org/0000-0003-1766-456X + + + Florian + Huber + + Netherlands eScience Center, Amsterdam, The Netherlands + Düsseldorf University of Applied Sciences, Düsseldorf, Germany + + https://orcid.org/0000-0002-3535-9406 + + + Dafne + van Kuppevelt + + Netherlands eScience Center, Amsterdam, The Netherlands + + https://orcid.org/0000-0002-2662-1994 + + + Ashwin Vishnu + Mohanan + + RISE Research Institutes of Sweden, Sweden + + https://orcid.org/0000-0002-2979-6327 + + + Colin + Sauze + + National Oceanography Centre, Liverpool, Great-Britain + + https://orcid.org/0000-0001-5368-9217 + + + Carsten + Schnober + + Netherlands eScience Center, Amsterdam, The Netherlands + + https://orcid.org/0000-0001-9139-1577 + + + Djura + Smits + + Netherlands eScience Center, Amsterdam, The Netherlands + + https://orcid.org/0000-0003-4096-0260 + + + Peter + Steinbach + + Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany + + https://orcid.org/0000-0002-4974-230X + + + Berend + Weel + + Netherlands eScience Center, Amsterdam, The Netherlands + + https://orcid.org/0000-0002-9693-9332 + + + Kjartan Thor + Wikfeldt + + RISE Research Institutes of Sweden, Sweden + + https://orcid.org/0000-0002-1655-3676 + + + Samantha + Wittke + + CSC - IT center for Science, Espoo, Finland + Aalto University, Espoo, Finland + + https://orcid.org/0000-0002-9625-7235 + + + + 10 + 19 + 2025 + + + 307 + + + 10.21105/jose.00307 + + + http://creativecommons.org/licenses/by/4.0/ + http://creativecommons.org/licenses/by/4.0/ + http://creativecommons.org/licenses/by/4.0/ + + + + Software archive + 10.5281/zenodo.8308391 + + + GitHub review issue + https://github.com/openjournals/jose-reviews/issues/307 + + + + 10.21105/jose.00307 + https://jose.theoj.org/papers/10.21105/jose.00307 + + + https://jose.theoj.org/papers/10.21105/jose.00307.pdf + + + + + + The Carpentries Curriculum Development Handbook + Becker + Becker, E., & Michonneau, F. (n.d.). The Carpentries Curriculum Development Handbook. Retrieved September 1, 2023, from https://cdh.carpentries.org/ + + + The Carpentries Workbench + The Carpentries Workbench. (n.d.). Retrieved September 1, 2023, from https://carpentries.github.io/workbench/ + + + Fast.ai - Practical Deep Learning for Coders + Fast.ai - Practical Deep Learning for Coders. (n.d.). Retrieved September 1, 2023, from https://course.fast.ai/ + + + Udemy - Basics of Deep Learning + Udemy + Udemy - Basics of Deep Learning. (n.d.). In Udemy. Retrieved September 1, 2023, from https://www.udemy.com/course/basics-of-deep-learning/ + + + Udemy - Tensorflow 2.0 Recurrent Neural Networks, LSTMs, GRUs + Udemy + Udemy - Tensorflow 2.0 Recurrent Neural Networks, LSTMs, GRUs. (n.d.). In Udemy. Retrieved September 1, 2023, from https://www.udemy.com/course/tensorflow-20-recurrent-neural-networks-lstms-grus/ + + + Udemy - Data Science: Intro To Deep Learning With Python + Udemy + Udemy - Data Science: Intro To Deep Learning With Python. (n.d.). In Udemy. Retrieved September 1, 2023, from https://www.udemy.com/course/complete-deep-learning-course-with-python/ + + + Coursera - Deep Learning + Coursera + Coursera - Deep Learning. (n.d.). In Coursera. Retrieved September 1, 2023, from https://www.coursera.org/specializations/deep-learning + + + freeCodeCamp.org - Learn PyTorch for Deep Learning + freeCodeCamp.org + 2022 + freeCodeCamp.org - Learn PyTorch for Deep Learning. (2022). In freeCodeCamp.org. https://www.freecodecamp.org/news/learn-pytorch-for-deep-learning-in-day/ + + + CSC- Practical Deep Learning + Eventilla + CSC- Practical Deep Learning. (n.d.). In Eventilla. Retrieved September 1, 2023, from https://ssl.eventilla.com/event/8aPek + + + Software Carpentry: Getting Scientists to Write Better Code by Making Them More Productive + Wilson + Computing in Science & Engineering + 6 + 8 + 10.1109/MCSE.2006.122 + 1558-366X + 2006 + Wilson, G. (2006). Software Carpentry: Getting Scientists to Write Better Code by Making Them More Productive. Computing in Science & Engineering, 8(6), 66–69. https://doi.org/10.1109/MCSE.2006.122 + + + Small Teaching: Everyday Lessons from the Science of Learning + Lang + 978-1-119-75554-8 + 2021 + Lang, J. M. (2021). Small Teaching: Everyday Lessons from the Science of Learning. John Wiley & Sons. ISBN: 978-1-119-75554-8 + + + Software Carpentry: Programming with Python. + Azalee Bostroem + GitHub + 2016 + Azalee Bostroem, Trevor Bekolay, & Valentina Staneva (eds). (2016). Software Carpentry: Programming with Python. In GitHub. https://github.com/swcarpentry/python-novice-inflammation, 10.5281/zenodo.57492 + + + Scikit-learn course + 2023 + Scikit-learn course. (2023). Inria. https://github.com/INRIA/scikit-learn-mooc + + + Introduction to artificial neural networks in Python (Carpentries Incubator) + Pollard + 2022 + Pollard, T., Peru, G., & Pontes Reis, E. (2022). Introduction to artificial neural networks in Python (Carpentries Incubator) (Version 0.1.0). https://github.com/carpentries-incubator/machine-learning-neural-python + + + Allisonhorst/palmerpenguins: v0.1.0 + Horst + 10.5281/zenodo.3960218 + 2020 + Horst, A. M., Hill, A. P., & Gorman, K. B. (2020). Allisonhorst/palmerpenguins: v0.1.0. Zenodo. https://doi.org/10.5281/zenodo.3960218 + + + Weather prediction dataset + Huber + 10.5281/ZENODO.4770936 + 2022 + Huber, F., Kuppevelt, D. van, Steinbach, P., Sauze, C., Liu, Y., & Weel, B. (2022). Weather prediction dataset. Zenodo. https://doi.org/10.5281/ZENODO.4770936 + + + The Dollar Street Dataset: Images Representing the Geographic and Socioeconomic Diversity of the World + Gaviria Rojas + Advances in Neural Information Processing Systems + 35 + 2022 + Gaviria Rojas, W., Diamos, S., Kini, K., Kanter, D., Janapa Reddi, V., & Coleman, C. (2022). The Dollar Street Dataset: Images Representing the Geographic and Socioeconomic Diversity of the World. Advances in Neural Information Processing Systems, 35, 12979–12990. https://papers.nips.cc/paper_files/paper/2022/hash/5474d9d43c0519aa176276ff2c1ca528-Abstract-Datasets_and_Benchmarks.html + + + MS2DeepScore: A novel deep learning similarity measure to compare tandem mass spectra + Huber + Journal of Cheminformatics + 1 + 13 + 10.1186/s13321-021-00558-4 + 1758-2946 + 2021 + Huber, F., Burg, S. van der, Hooft, J. J. J. van der, & Ridder, L. (2021). MS2DeepScore: A novel deep learning similarity measure to compare tandem mass spectra. Journal of Cheminformatics, 13(1), 84. https://doi.org/10.1186/s13321-021-00558-4 + + + Dollar street 10 - 64x64x3 + burg + 10.5281/zenodo.10970014 + 2024 + burg, S. van der. (2024). Dollar street 10 - 64x64x3. Zenodo. https://doi.org/10.5281/zenodo.10970014 + + + CIFAR-10 and CIFAR-100 datasets + CIFAR-10 and CIFAR-100 datasets. (n.d.). Retrieved February 11, 2025, from https://www.cs.toronto.edu/~kriz/cifar.html + + + + + + diff --git a/jose.00307/10.21105.jose.00307.pdf b/jose.00307/10.21105.jose.00307.pdf new file mode 100644 index 0000000..a6185ad Binary files /dev/null and b/jose.00307/10.21105.jose.00307.pdf differ diff --git a/jose.00307/paper.jats/10.21105.jose.00307.jats b/jose.00307/paper.jats/10.21105.jose.00307.jats new file mode 100644 index 0000000..48dd887 --- /dev/null +++ b/jose.00307/paper.jats/10.21105.jose.00307.jats @@ -0,0 +1,896 @@ + + +
+ + + + +Journal of Open Source Education +JOSE + +2577-3569 + +Open Journals + + + +307 +10.21105/jose.00307 + +Introduction to deep learning: Carpentries-style hands-on +lesson material for introducing researchers to deep +learning + + + +https://orcid.org/0000-0003-1250-6968 + +van der Burg +Sven A. + + + + +https://orcid.org/0000-0002-7896-2969 + +Chandramouli +Pranav + + + + +https://orcid.org/0000-0002-1784-2920 + +Fouilloux +Anne + + + + +https://orcid.org/0000-0002-1409-8358 + +Geng +Cunliang + + + + +https://orcid.org/0000-0003-1766-456X + +Hodges +Toby + + + + +https://orcid.org/0000-0002-3535-9406 + +Huber +Florian + + + + + +https://orcid.org/0000-0002-2662-1994 + +van Kuppevelt +Dafne + + + + +https://orcid.org/0000-0002-2979-6327 + +Mohanan +Ashwin Vishnu + + + + +https://orcid.org/0000-0001-5368-9217 + +Sauze +Colin + + + + +https://orcid.org/0000-0001-9139-1577 + +Schnober +Carsten + + + + +https://orcid.org/0000-0003-4096-0260 + +Smits +Djura + + + + +https://orcid.org/0000-0002-4974-230X + +Steinbach +Peter + + + + +https://orcid.org/0000-0002-9693-9332 + +Weel +Berend + + + + +https://orcid.org/0000-0002-1655-3676 + +Wikfeldt +Kjartan Thor + + + + +https://orcid.org/0000-0002-9625-7235 + +Wittke +Samantha + + + + + + +Netherlands eScience Center, Amsterdam, The +Netherlands + + + + +Simula Research Laboratory, Oslo, Norway + + + + +Düsseldorf University of Applied Sciences, Düsseldorf, +Germany + + + + +Helmholtz-Zentrum Dresden-Rossendorf, Dresden, +Germany + + + + +National Oceanography Centre, Liverpool, +Great-Britain + + + + +CSC - IT center for Science, Espoo, Finland + + + + +Aalto University, Espoo, Finland + + + + +The Carpentries, USA + + + + +RISE Research Institutes of Sweden, Sweden + + + + +8 +8 +2023 + +8 +92 +307 + +Authors of papers retain copyright and release the +work under a Creative Commons Attribution 4.0 International License (CC +BY 4.0) +2025 +The article authors + +Authors of papers retain copyright and release the work under +a Creative Commons Attribution 4.0 International License (CC BY +4.0) + + + +Python +deep learning +machine learning +Keras +neural networks + + + + + + Summary +

This article describes a hands-on introduction to the first steps + in deep learning, intended for researchers who are familiar with + (non-deep) machine learning.

+

The use of deep learning has seen a sharp increase in popularity + and applicability over the last decade. While deep learning can be a + useful tool for researchers from a wide range of domains, taking the + first steps in the world of deep learning can be somewhat + intimidating. This introduction aims to cover the fundamentals of deep + learning in a practical and hands-on manner. By the end of the course, + students will be able to train their first neural network and + understand the subsequent steps needed to improve the model.

+

The lesson starts by explaining the basic concepts of neural + networks, and then guides learners through the different steps of a + deep learning workflow. + After following this lesson, learners will be able to prepare data for + deep learning, implement a basic deep learning model in Python with + Keras, and monitor and troubleshoot the training process. In addition, + they will be able to implement and understand different layer types, + such as convolutional layers and dropout layers, and apply transfer + learning.

+

We use data with permissive licenses and designed for real world + use cases:

+ + +

The Penguin dataset (Horst et al. + (2020))

+
+ +

The Weather prediction dataset (Huber et al. + (2022))

+
+ +

The Dollar Street Dataset (Gaviria Rojas et al. + (2022)) + is representative and contains accurate demographic information to + ensure their robustness and fairness, especially for smaller + subpopulations.

+
+
+
+ + Statement of Need +

This lesson addresses the need for an introductory lesson on deep + learning that is open-source, and can be used by instructors in a + workshop as well as for self-study. While generally usable, its target + audience are academic researchers.

+

There are many free online course materials on deep learning, see + for example: Fast.ai - Practical Deep Learning for + Coders + (n.d.); + “Udemy - Basics of Deep Learning” + (n.d.); + “Udemy - Tensorflow 2.0 Recurrent Neural Networks, LSTMs, GRUs” + (n.d.); + “Free Deep Learning Tutorial - Data Science” + (n.d.); + “Coursera - Deep Learning” + (n.d.); + “freeCodeCamp.org + - Learn PyTorch for Deep Learning” + (2022).

+

Nonetheless, these resources are often not available open-source + and can thus not be easily adapted to the students’ needs. Also, these + resources are intended to use for self-study. Our material can be used + for self-study, but it is primarily developed for instructors to use + in a workshop. In addition, although a diverse range of online courses + already exists, few are targeted towards academic researchers.

+

There is another Carpentries lesson on deep learning: Introduction + to artificial neural networks in Python (Pollard et al. + (2022)). + That lesson takes a different angle to deep learning, focusing on + computer vision with the application on medical images. Whereas this + lesson is a general introduction to applied deep learning showing + various applications and is more mature.

+

Many computing centers offer (local) deep learning courses, such as + “CSC- Practical Deep Learning” + (n.d.). + But the lesson material, if it is available, is not easily adopted + outside the course organisation.

+

The pedagogical approach of this lesson is both to make learners + familiar with the key concepts, and let them practice with how to + implement them – eventually resulting in an increase in confidence and + the conviction that ‘I can do this myself’. The key to getting there + is live coding: before the course, learners have to setup a working + environment on their own computer. During the course, learners type in + the commands that are explained by the instructor on their own + computer. This design is based on the Software Carpentry + (Wilson, + 2006) philosophy. Live coding ensures that learners master the + programmatic implementation of deep learning at the end of the course. + We believe that this makes our lesson a unique and crucial + resource.

+

Researchers can often only free a limited amount of time (maximum 5 + consecutive days), since they are so involved in their daily work. To + accomplish this, we created a lesson that can be taught in 2 + consecutive days or 4 half days.

+

Demand for our workshops and feedback gathered from students + demonstrated the need for a low-threshold lesson that lets researchers + take the first steps in the field of deep learning. This impression + was validated by other instructors who taught the lesson independently + to their own audiences and provided us with feedback on their + experience.

+
+ + Lesson Development +

In 2018, the Netherlands eScience Center initiated the development + of this lesson to fill the gap identified above. Over the years, the + lesson has attracted a broad community of individuals and + organizations that have used the material for teaching workshops, and + contributed to the improvement of the lesson significantly.

+

The diversity of the involved parties has facilitated the + integration of various viewpoints on the lesson material. Apart from + the feedback gathered from students while teaching the workshop (see + below), the mix of contributors includes educators, data scientists, + and, most prominently, (research) software engineers. Some of them + have had years of experience in the deep learning domain, while others + have used the lesson as a first step into the field.

+

Development sprints of typically two full working days have + regularly facilitated focussed collaboration sessions that have + brought together various contributors to tackle specific issues + identified in the lesson material. These sessions have also provided a + fruitful ground for discussing the various experiences with and + insights about the material. They have facilitated the iterative + improvement of the material, resulting in a mature and well-tested set + of episodes.

+
+ + Instructional design +

This lesson material was designed using the concepts from The + Carpentries Curriculum Development Handbook + (Becker + & Michonneau, n.d.). Most importantly, we used ‘backward + design’: we started with identifying learning objectives, the core + skills and concepts that learners should acquire as a result of the + lesson. Next, exercises were designed to assess whether these + objectives are met. Eventually, the content is written to teach the + skills and concepts learners need to successfully complete the + exercises and, it follows, meet the learning objectives.

+

Live coding is central to this approach: the lesson is built up of + small blocks. In each block first the instructor demonstrates how to + do something, and students follow along on their own computer. Then, + the students work independently on exercises individually or in groups + to test their skills. This approach integrates opportunities for + guided practice throughout the lesson, promoting learning by helping + learners build up a functioning mental model of the domain and + transfer new knowledge from working memory to long-term memory. This + is in accordance with research-based successful teaching strategies + (Lang, + 2021).

+

The lesson material is built in the new lesson template: + Carpentries Workbench + (The + Carpentries Workbench, n.d.). This makes the lesson + material a complete self-study resource. But it also serves as lesson + material for the instructor teaching the lesson through live-coding, + in that case the lesson material is only shared with students after + the workshop as a reference. The lesson material can be toggled to the + ‘instructor view’. This allows to provide instructor notes on how to + approach teaching the lesson, and these can even be included at the + level of the lesson content. In addition, the Carpentries Workbench + prioritises accessibility of the content, for example by having + clearly visible figure captions and promoting alt-texts for + pictures.

+

The lesson is split into a general introduction, and 4 episodes + that cover 3 distinct increasingly more complex deep learning + problems. Each of the deep learning problems is approached using the + same 10-step deep learning workflow + (https://carpentries-lab.github.io/deep-learning-intro/1-introduction.html#deep-learning-workflow).

+

By going through the deep learning cycle three times with different + problems, learners become increasingly confident in applying this deep + learning workflow to their own projects. We end with an outlook + episode. Firstly, the outlook eposide discusses a real-world + application of deep learning in chemistry + (Huber + et al., 2021). In addition, it discusses bias in datasets, + large language models, and good practices for organising deep learning + projects. Finally, we end with ideas for next steps after finishing + the lesson.

+
+ + Feedback +

This course was taught 13 times over the course of 4 years, both + online and in-person, by the Netherlands eScience Center (Netherlands, + https://www.esciencecenter.nl/) and Helmholtz-Zentrum + Dresden-Rossendorf (Germany, https://www.hzdr.de/). Apart from the + core group of contributors, the workshop was also taught at at least 3 + independent institutes, namely: University of Wisconson-Madison (US, + https://www.wisc.edu/), University of Auckland (New Zealand, + https://www.auckland.ac.nz/), and EMBL Heidelberg (Germany, + https://www.embl.org/sites/heidelberg/).

+

An up-to-date list of workshops that the authors are aware of + having using this lesson can be found in a + workshops.md file in the + GitHub + repository.

+

In general, adoption of the lesson material by the instructors not + involved in the project went well. The feedback gathered from our own + and others’ teachings was used to polish the lesson further.

+ + Student responses +

The feedback we gathered from students is in general very + positive, with some responses from students to the question ‘What + was your favourite or most useful part of the workshop. Why?’ + further confirming our statement of need:

+ +

I enjoyed the live coding and playing with the models + to see how it would effect the results. It felt hands on and made + it easy for me to understand the concepts.

+
+ +

Well-defined steps to be followed in training a model + is very useful. Examples we worked on are quite nice.

+
+ +

The doing part, that really helps to get the theory + into practice.

+
+

Below are two tables summarizing results from our post-workshop + survey. We use the students’ feedback to continuously improve the + lesson.

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
STRONGLY DISAGREEDISAGREEUNDECIDEDAGREESTRONGLY AGREETOTALWEIGHTED AVERAGE
I can immediately apply what I learned at this + workshop.056198383,8
The setup and installation instructions for the lesson + were complete and easy to follow.0041321384,4
Examples and tasks in the lesson were relevant and + authentic0051914384,2
+
+

Table 1: Agreement on statements by students from 2 workshops + taught at the Netherlands eScience Center. The results from these 2 + workshops are a good representation of the general feedback we get + when teaching this workshop.

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
POORFAIRGOODVERY GOODEXCELLENTN/ATOTALWEIGHTED AVERAGE
Introduction into Deep Learning0 (0%)2 (5%)10 (27%)8 (22%)17 (46%)0 (0%)374,1
Classification by a Neural Network using Keras (penguins + dataset)0 (0%)1 (3%)5 (13%)16 (42%)16 (42%)0 (0%)384,2
Monitoring and Troubleshooting the learning process + (weather dataset)0 (0%)0 (0%)4 (11%)18 (47%)16 (42%)0 (0%)384,3
Advanced layer types (CIFAR-10 dataset)0 (0%)2 (5%)5 (13%)7 (18%)16 (42%)8 (21%)384,2
+
+

Table 2: Quality of the different episodes of the workshop as + rated by students from 2 workshops taught at the Netherlands + eScience Center. The results from these 2 workshops are a good + representation of the general feedback we get when teaching this + workshop.

+
+ + Carpentries Lab review process +

Prior to submitting this paper the lesson went through the + substantial review in the process of becoming an official + Carpentries Lab (https://carpentries-lab.org/) lesson. This led to a + number of improvements to the lesson. In general the accessibility + and user-friendliness improved, for example by updating alt-texts + and using more beginner-friendly and clearer wording. Additionally, + the instructor notes were improved and many missing explanations of + important deep learning concepts were added to the lesson.

+

Most importantly, the reviewers pointed out that the CIFAR-10 + (CIFAR-10 + and CIFAR-100 Datasets, n.d.) dataset that we + initially used does not have a license. We were surprised to find + out that this dataset, that is one of the most widely used datasets + in the field of machine learning and deep learning, is actually + unethically scraped from the internet without permission from image + owners. As an alternative we now use ‘Dollar street 10’ + (burg, + 2024), a dataset that was adapted for this lesson from The + Dollar Street Dataset (Gaviria Rojas et al. + (2022)). + The Dollar Street Dataset is representative and contains accurate + demographic information to ensure their robustness and fairness, + especially for smaller subpopulations. In addition, it is a great + entry point to teach learners about ethical AI and bias in + datasets.

+

You can find all details of the review process on GitHub: + https://github.com/carpentries-lab/reviews/issues/25.

+
+
+ + Conclusion +

This lesson can be taught as a stand-alone workshop to students + already familiar with machine learning and Python. It can also be + taught in a broader curriculum after an introduction to Python + programming (for example: Azalee Bostroem et al. + (2016)) + and an introduction to machine learning (for example: + Scikit-Learn Course + (2023)). + Concluding, the described lesson material is a unique and essential + resource aimed at researchers and designed specifically for a + live-coding teaching style. Hopefully, it will help many researchers + to set their first steps in a successful application of deep learning + to their own domain.

+
+ + Acknowledgements +

We would like to thank all instructors and helpers that taught the + course, and the community of people that left contributions to the + project, no matter how big or small. Also, we thank Chris Endemann + (University of Wisconson-Madison, US, https://www.wisc.edu/), Nidhi + Gowdra (University of Auckland, New Zealand, + https://www.auckland.ac.nz/), Renato Alves and Lisanna Paladin (EMBL + Heidelberg, Germany, https://www.embl.org/sites/heidelberg/), that + piloted this workshop at their institutes. We thank the Carpentries + for providing such a great framework for developing this lesson + material. We thank Sarah Brown, Johanna Bayer, and Mike Laverick for + giving us excellent feedback on the lesson during the Carpentries Lab + review process. We thank all students enrolled in the workshops that + were taught using this lesson material for providing us with + feedback.

+
+ + + + + + + + BeckerErin + MichonneauFrançois + + The Carpentries Curriculum Development Handbook + 20230901 + https://cdh.carpentries.org/ + + + + + The Carpentries Workbench + 20230901 + https://carpentries.github.io/workbench/ + + + + + Fast.ai - Practical Deep Learning for Coders + 20230901 + https://course.fast.ai/ + + + + + Udemy - Basics of Deep Learning + Udemy + 20230901 + https://www.udemy.com/course/basics-of-deep-learning/ + + + + + Udemy - Tensorflow 2.0 Recurrent Neural Networks, LSTMs, GRUs + Udemy + 20230901 + https://www.udemy.com/course/tensorflow-20-recurrent-neural-networks-lstms-grus/ + + + + + Udemy - Data Science: Intro To Deep Learning With Python + Udemy + 20230901 + https://www.udemy.com/course/complete-deep-learning-course-with-python/ + + + + + Coursera - Deep Learning + Coursera + 20230901 + https://www.coursera.org/specializations/deep-learning + + + + + freeCodeCamp.org - Learn PyTorch for Deep Learning + freeCodeCamp.org + 202210 + 20230901 + https://www.freecodecamp.org/news/learn-pytorch-for-deep-learning-in-day/ + + + + + CSC- Practical Deep Learning + Eventilla + 20230901 + https://ssl.eventilla.com/event/8aPek + + + + + + WilsonG. + + Software Carpentry: Getting Scientists to Write Better Code by Making Them More Productive + Computing in Science & Engineering + 200611 + 8 + 6 + 1558-366X + 10.1109/MCSE.2006.122 + 66 + 69 + + + + + + LangJames M. + + Small Teaching: Everyday Lessons from the Science of Learning + John Wiley & Sons + 202108 + 978-1-119-75554-8 + + + + + + Azalee Bostroem + Trevor Bekolay + Valentina Staneva (eds) + + Software Carpentry: Programming with Python. + GitHub + 201606 + 20230901 + https://github.com/swcarpentry/python-novice-inflammation, 10.5281/zenodo.57492 + + + + + Scikit-learn course + Inria + 202309 + 20230901 + https://github.com/INRIA/scikit-learn-mooc + + + + + + PollardTom + PeruGiacomo + Pontes ReisEduardo + + Introduction to artificial neural networks in Python (Carpentries Incubator) + 202205 + https://github.com/carpentries-incubator/machine-learning-neural-python + + + + + + HorstAllison M. + HillAlison Presmanes + GormanKristen B. + + Allisonhorst/palmerpenguins: v0.1.0 + Zenodo + 202007 + https://doi.org/10.5281/zenodo.3960218 + 10.5281/zenodo.3960218 + + + + + + HuberFlorian + KuppeveltDafne van + SteinbachPeter + SauzeColin + LiuYang + WeelBerend + + Weather prediction dataset + Zenodo + 202209 + 20250114 + https://zenodo.org/record/4770936 + 10.5281/ZENODO.4770936 + + + + + + Gaviria RojasWilliam + DiamosSudnya + KiniKeertan + KanterDavid + Janapa ReddiVijay + ColemanCody + + The Dollar Street Dataset: Images Representing the Geographic and Socioeconomic Diversity of the World + Advances in Neural Information Processing Systems + 202212 + 20250114 + 35 + https://papers.nips.cc/paper_files/paper/2022/hash/5474d9d43c0519aa176276ff2c1ca528-Abstract-Datasets_and_Benchmarks.html + 12979 + 12990 + + + + + + HuberFlorian + BurgSven van der + HooftJustin J. J. van der + RidderLars + + MS2DeepScore: A novel deep learning similarity measure to compare tandem mass spectra + Journal of Cheminformatics + 202110 + 20250211 + 13 + 1 + 1758-2946 + https://doi.org/10.1186/s13321-021-00558-4 + 10.1186/s13321-021-00558-4 + 84 + + + + + + + burgSven van der + + Dollar street 10 - 64x64x3 + Zenodo + 202404 + 20250211 + https://zenodo.org/records/10970014 + 10.5281/zenodo.10970014 + + + + + CIFAR-10 and CIFAR-100 datasets + 20250211 + https://www.cs.toronto.edu/~kriz/cifar.html + + + + +