• Corpus ID: 246864036

A Guide to Computational Reproducibility in Signal Processing and Machine Learning

  title={A Guide to Computational Reproducibility in Signal Processing and Machine Learning},
  author={Josephine Shenouda and Waheed Uz Zaman Bajwa},
Computational reproducibility is a growing problem that has been extensively studied among computational researchers and within the signal processing and machine learning research community. However, with the changing landscape of signal processing and machine learning research come new obstacles and unseen challenges in creating reproducible experiments. Due to these new challenges most computational experiments have become difficult, if not impossible, to be reproduced by an independent… 

Surveying 5G Techno-Economic Research to Inform the Evaluation of 6G Wireless Technologies

The survey discusses emerging trends from the 5G techno-economic literature and makes five key recommendations for the design and standardization of Next Generation 6G wireless technologies.



Reproducible research in signal processing

If the experiments are performed on a large data set, the algorithm is compared to the state-of-the-art methods, the code and/or data are well documented and available online, the community will all benefit and make it easier to build upon each other's work.

A Step Toward Quantifying Independently Reproducible Machine Learning Research

Man manually attempting to implement 255 papers published from 1984 until 2017, recording features of each paper, and performing statistical analysis of the results.

State of the Art: Reproducibility in Artificial Intelligence

The reproducibility scores decrease with in- creased documentation requirements and improvement over time is found, indicating that AI research is not documented well enough to reproduce the reported results.

TensorFlow: A system for large-scale machine learning

The TensorFlow dataflow model is described and the compelling performance that Tensor Flow achieves for several real-world applications is demonstrated.

Towards computational reproducibility: researcher perspectives on the use and sharing of software

It is found that researchers create, use, and share software in a wide variety of forms for a wide range of purposes, including data collection, data analysis, data visualization, data cleaning and organization, and automation.

Making massive computational experiments painless

ClusterJob (CJ) is presented, an efficient computing environment that researchers have used to conduct and share million-CPU-hour experiments in a painless and reproducible way and a taxonomy of some of the desiderata which such paradigms should offer.

An introduction to Docker for reproducible research

How the popular emerging technology Docker combines several areas from systems research - such as operating system virtualization, cross-platform portability, modular re-usable elements, versioning, and a 'DevOps' philosophy, to address these challenges is examined.

Learning Mixtures of Separable Dictionaries for Tensor Data: Analysis and Algorithms

This work proposes learning a mixture of separable dictionaries to better capture the structure of tensor data by generalizing the separable dictionary learning model.

Gradient-based learning applied to document recognition

This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.

Scikit-learn: Machine Learning in Python

Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing