Conference item
Deep learning programming by all
- Abstract:
- We describe an open-source blocks-based programming library in Snap! [Harvey and Mönig, 2010] that enables non-experts to construct machine learning applications. The library includes blocks for creating models, defining the training and validation datasets, training, and prediction. We present several sample applications: approximating mathematical functions from examples, attempting to predict the number of influenza infections given historical weather data, predicting ratings of generated images, naming random colours, question answering, and learning to win when playing Tic Tac Toe.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, pdf, 1021.2KB, Terms of use)
-
- Publication website:
- http://www.constructionismconf.org/proceedings/
Authors
- Publisher:
- Constructionism
- Publication date:
- 2020-05-26
- Acceptance date:
- 2020-01-28
- Event title:
- Constructionism 2020
- Event location:
- Dublin, Ireland
- Event website:
- http://www.constructionismconf.org/
- Event start date:
- 2020-05-26
- Event end date:
- 2020-05-29
- ISBN:
- 9781911566090
- Language:
-
English
- Keywords:
- Pubs id:
-
1106909
- Local pid:
-
pubs:1106909
- Deposit date:
-
2020-05-26
- ARK identifier:
Terms of use
- Copyright holder:
- Kahn et al.
- Copyright date:
- 2020
- Rights statement:
- © Kahn et al 2020. Open Access Creative Commons Attribution 4.0 International License.
- Notes:
- This paper was accepted for presentation at Constructionism 2020, Dublin, Ireland, May 2020. The conference was cancelled due to COVID-19, but the proceedings are available online from Constructionism at: http://www.constructionismconf.org/proceedings/
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record