On the Performance of Convolutional Neural Networks Initialized with Gabor Filters

When observing a fully trained CNN, researchers have found that the pattern on the kernel filters (convolution window) of the receptive convolutional layer closely resembles the Gabor filters. Gabor filters have existed for a long time, and researchers have been using them for texture analysis. Given the nature and purpose of the receptive layer of CNN, Gabor filters could act as a suitable replacement strategy for the randomly initialized kernels of the receptive layer in CNN, which could potentially boost the performance without any regard to the nature of the dataset. The findings in this thesis show that when low-level kernel filters are initialized with Gabor filters, there is a boost in accuracy, Area Under ROC (Receiver Operating Characteristic) Curve (AUC), minimum loss, and speed in some cases based on the complexity of the dataset. [pdf, bib]

Different Gabor filters with different values for \lambda, \theta, and \gamma. Different parameters will change filter properties.

How High can you Fly? LCC Passenger Dissatisfaction

This study provides a better understanding of the LCC passenger dissatisfaction phenomenon, as we now have an idea of which themes are important and require urgent attention. The findings show that over 10 years, the LCC passenger dissatisfaction criteria evolved, meaning that LCCs should be strongly aware of areas of concern in order to maintain passenger satisfaction. Based on classic data analytics, four themes – flight delay, ground staff attitude, luggage handling, and seat comfort – were identified as playing a crucial role in passenger dissatisfaction. Interestingly, LCC passengers were not found to have a problem with cabin crew attitude. Two possible reasons for the major themes of ground staff dissatisfaction may simply be that LCC ground staff lack training and that passengers expect ground staff to have the authority to make decisions and to be aware of passengers’ needs. Overall, when ground staff is not able to deal with passengers’ demands, passengers feel dissatisfied. In addition, the study found that the check-in counter, food, airline ground announcements, airline responses, cleanliness and additional/personal costs are secondary themes in passenger dissatisfaction. This study, therefore, clearly shows that LCCs should prioritize their efforts to minimize passenger dissatisfaction by firstly dealing with the primary themes of passenger dissatisfaction. [pdf, bib]

The Final Themes of LCC Passenger Dissatisfaction

Special Issue “Standards and Ethics in AI”

Upcoming Rolling Deadline: May 31, 2022

Dear Colleagues,

There is a swarm of artificial intelligence (AI) ethics standards and regulations being discussed, developed, and released worldwide. The need for an academic discussion forum for the application of such standards and regulations is evident. The research community needs to keep track of any updates for such standards, and the publication of use cases and other practical considerations for such.

This Special Issue of the journal AI on “Standards and Ethics in AI” will publish research papers on applied AI ethics, including the standards in AI ethics. This implies interactions among technology, science, and society in terms of applied AI ethics and standards; the impact of such standards and ethical issues on individuals and society; and the development of novel ethical practices of AI technology. The journal will also provide a forum for the open discussion of resulting issues of the application of such standards and practices across different social contexts and communities. More specifically, this Special Issue welcomes submissions on the following topics:

  • AI ethics standards and best practices;
  • Applied AI ethics and case studies;
  • AI fairness, accountability, and transparency;
  • Quantitative metrics of AI ethics and fairness;
  • Review papers on AI ethics standards;
  • Reports on the development of AI ethics standards and best practices.

Note, however, that manuscripts that are philosophical in nature might be discouraged in favor of applied ethics discussions where readers have a clear understanding of the standards, best practices, experiments, quantitative measurements, and case studies that may lead readers from academia, industry, and government to find actionable insight.

Dr. Pablo Rivas
Dr. Gissella Bejarano
Dr. Javier Orduz
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AI is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open-access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI’s English editing service prior to publication or during author revisions.

International Conference on Emergent and Quantum Technologies (ICEQT’22)

July 25-28, 2022 — Las Vegas, NV

Dear Colleagues,

Quantum computing is an emerging interdisciplinary research area at the intersection of mathematics, physics, and engineering. Quantum computing requires experts, and specialists from STEM areas to assure scientific rigor and to keep up with technological advances.

The main goal of organizing ICEQT’22 is to share knowledge about the recent advancements in the field of QML and build a forum for discussions on this topic for researchers working in this field as well as machine learning researchers, attending The 2022 World Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE’22), who are interested in applying AI to enhance quantum computing algorithms.

In recent years, we have observed a significant amount of published research papers in the quantum machine learning domain. There is an increasing interest from machine learning researchers to apply AI to the quantum computing domain (and vice versa). Therefore, we invite all contributions in the following areas:

AI for Quantum
* Machine learning for improved quantum algorithm performance
* Machine learning for quantum control
* Machine learning for building better quantum hardware
Quantum technologies and applications
* Quantum computing: models and paradigms
* Fairness/ethics with quantum machine learning
* Quantum algorithms for hyperparameter tuning (Quantum computing for AutoML)
* Theory of Quantum-enhanced Machine Learning
* Quantum Machine Learning Algorithms based on Grover search
* Quantum-enhanced Reinforcement Learning
* Quantum computing, models and paradigms such as Quantum Annealing,
* Quantum Sampling
Quantum computing foundations
* Quantum computing: models and paradigms
* Applications of Quantum Machine Learning
* Quantum Tensor Networks and their Applications in QML
* Quantum algorithms for Linear Systems of Equations, and other algorithms such as Quantum Neural Networks, Quantum Hidden Markov Models, Quantum PCA, Quantum SVM, Quantum Autoencoders, Quantum Transfer Learning, Quantum Boltzmann machines, Grover, Shor, and others.

You are invited to submit a paper for consideration. ALL ACCEPTED PAPERS will be published in the corresponding proceedings by Publisher:
Springer Nature – Book Series: Transactions on Computational Science & Computational Intelligence
https://www.springer.com/series/11769

Prospective authors are invited to submit their papers by uploading them to the evaluation website at:
https://american-cse.org/drafts/

For more information, visit our website:
https://baylor.ai/iceqt/

Important Deadlines

March 31, 2022: Submission of papers: https://american-cse.org/drafts/
– Full/Regular Research Papers (maximum of 10 pages)
– Short Research Papers (maximum of 6 pages)
– Abstract/Poster Papers (maximum of 3 pages)

April 18, 2022: Notification of acceptance (+/- two days)

May 12, 2022: Final papers + Registration

June 22, 2022: Hotel Room reservation (for those who are physically attending the conference).

July 25-28, 2022: The 2022 World Congress in Computer Science, Computer Engineering, and Applied Computing (CSCE’22: USA)
Which includes the International Conference on Emergent and Quantum Technologies (ICEQT’22)

Chairs:
Dr. Javier Orduz, Baylor University
Dr. Pablo Rivas, Baylor University

An Adversarial Neural Cryptography Approach to Integrity Checking: Learning to Secure Data Communications

Securing communications is an increasingly challenging problem. While communication channels can be secured using strong ciphers, attackers who gain access to the channel can still perform certain types of attacks. One way to mitigate such attacks is to verify the integrity of exchanging messages between two parties or more. While there are robust integrity check mechanisms currently, these lack variety, and very few are based on machine learning. This paper presents a methodology for performing an integrity check inspired by recent advances in neural cryptography. We provide formal, mathematical functions and an optimization problem for training an adversarial neural cryptography architecture. The proposed neural architectures can adequately solve the problem. In our experiments, a receiver can verify if incoming messages are authentic or altered with an accuracy greater than 99%. This work expands the repertoire of integrity checking methodologies, provides a unique perspective based on neural networks and facilitates data security and privacy. Paper: [ bib , pdf ]

Training model for integrity check

A review of Earth Artificial Intelligence

In recent years, Earth system sciences are urgently calling for innovation on improving accuracy, enhancing model intelligence level, scaling up operation, and reducing costs in many subdomains amid the exponentially accumulated datasets and the promising artificial intelligence (AI) revolution in computer science. This paper presents work led by the NASA Earth Science Data Systems Working Groups and ESIP machine learning cluster to give a comprehensive overview of AI in Earth sciences. It holistically introduces the current status, technology, use cases, challenges, and opportunities, and provides all the levels of AI practitioners in geosciences with an overall big picture and to “blow away the fog to get a clearer vision” about the future development of Earth AI. The paper covers all the major spheres in the Earth system and investigates representative AI research in each domain. Widely used AI algorithms and computing cyberinfrastructure are briefly introduced. The mandatory steps in a typical workflow of specializing AI to solve Earth scientific problems are decomposed and analyzed. Eventually, it concludes with the grand challenges and reveals the opportunities to give some guidance and pre-warnings on allocating resources wisely to achieve the ambitious Earth AI goals in the future. [pdf, bib]

Challenges and opportunities.