Abstract
Visual programming languages make programming more accessible for novices, which open more opportunities to innovate and develop problem-solving skills. Besides, deep learning is one of the trending computer science fields that has a profound impact on our daily life, and it is important that young people are aware of how our world works. In this study, we partially attribute the difficulties novices face in building deep learning models to the used programming language. This paper presents DeepScratch, a new programming language extension to Scratch that provides powerful language elements to facilitate building and learning about deep learning models. We present the implementation process of DeepScratch, and explain the syntactical definition and the lexical definition of the extended vocabulary. DeepScratch provides two options to implement deep learning models: training a neural network based on built-in datasets and using pre-trained deep learning models. The two options are provided to serve different age groups and educational levels. The preliminary evaluation shows the usability and the effectiveness of this extension as a tool for kids to learn about deep learning.
Highlights
Programming nowadays is considered an essential skill and has been introduced in a novice level for different ages
Deep learning has a profound impact on our daily life and it is important that young people are aware of how our world works
DeepScratch provides two options to implement deep learning models: training a neural network based on built-in datasets, or using pre-trained deep learning models
Summary
Programming nowadays is considered an essential skill and has been introduced in a novice level for different ages. Visual programming languages allow users to develop programs by manipulating elements graphically instead of writing a program as a text. These languages can potentially allow young people to acquire the computational concepts more by reducing unnecessary syntax and facilitating the use of dragging and snapping the command blocks. With such features, these frameworks can help reduce the cognitive load on novices by allowing them to focus on the logic and structures of a program rather than worrying about the syntax and the mechanism of coding [3]. Several block-based programming language were designed after AgentSheet, such as Squeak eToys, Alice, and Scratch [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
