Towards A Visual Programming Tool to Create Deep Learning Models
This addresses the barrier for non-programmers in fields like medicine and finance to create deep learning models, though it appears incremental as it builds on existing model structures.
The paper tackles the problem of deep learning developers needing to learn programming languages by introducing DeepBlocks, a visual programming tool that allows designing, training, and evaluating models without coding, with results showing developers could visually design complex architectures.
Deep Learning (DL) developers come from different backgrounds, e.g., medicine, genomics, finance, and computer science. To create a DL model, they must learn and use high-level programming languages (e.g., Python), thus needing to handle related setups and solve programming errors. This paper presents DeepBlocks, a visual programming tool that allows DL developers to design, train, and evaluate models without relying on specific programming languages. DeepBlocks works by building on the typical model structure: a sequence of learnable functions whose arrangement defines the specific characteristics of the model. We derived DeepBlocks' design goals from a 5-participants formative interview, and we validated the first implementation of the tool through a typical use case. Results are promising and show that developers could visually design complex DL architectures.