LGMLJun 11, 2019

Improving Reproducible Deep Learning Workflows with DeepDIVA

arXiv:1906.04736v16 citations
Originality Incremental advance
AI Analysis

This addresses the issue of frustrating reproducibility for researchers in the machine learning community, though it is incremental as it builds on existing trends in reproducible workflows.

The paper tackles the problem of reproducibility in deep learning research by introducing DeepDIVA, a framework that facilitates easy experimentation and reproduction, offering features like boilerplate code, experiment management, and hyper-parameter optimization.

The field of deep learning is experiencing a trend towards producing reproducible research. Nevertheless, it is still often a frustrating experience to reproduce scientific results. This is especially true in the machine learning community, where it is considered acceptable to have black boxes in your experiments. We present DeepDIVA, a framework designed to facilitate easy experimentation and their reproduction. This framework allows researchers to share their experiments with others, while providing functionality that allows for easy experimentation, such as: boilerplate code, experiment management, hyper-parameter optimization, verification of data integrity and visualization of data and results. Additionally, the code of DeepDIVA is well-documented and supported by several tutorials that allow a new user to quickly familiarize themselves with the framework.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes