McKernel: A Library for Approximate Kernel Expansions in Log-linear Time.

Dear Colleagues and Friends,
We are pleased to announce the release (v2.2) of McKernel: A Library for Approximate Kernel Expansions in Log-linear Time ( https://arxiv.org/pdf/1702.08159.pdf).
Abstract:
McKernel introduces a framework to use kernel approximates in the minibatch setting with Stochastic Gradient Descent (SGD) as an alternative to Deep Learning. Based on Random Kitchen Sinks [Rahimi and Recht 2007], we provide a C++ library for Large-scale Machine Learning. It contains a CPU optimized implementation of the algorithm in [Le et al. 2013], that allows the computation of approximated kernel expansions in log-linear time. The algorithm requires to compute the product of matrices Walsh Hadamard. A cache friendly Fast Walsh Hadamard that achieves compelling speed and outperforms current state-of-the-art methods has been developed. McKernel establishes the foundation of a new architecture of learning that allows to obtain large-scale non-linear classification combining lightning kernel expansions and a linear classifier. It travails in the mini-batch setting working analogously to Neural Networks. We show the validity of our method through extensive experiments on MNIST and FASHION MNIST [Xiao et al. 2017].
Code (by Curtó and Zarza):
Please also check its follow-up work:
Doctor of Crosswise: Reducing Over-parametrization in Neural Networks ( https://arxiv.org/pdf/1905.10324.pdf).
Abstract:
Dr. of Crosswise proposes a new architecture to reduce over-parametrization in Neural Networks. It introduces an operand for rapid computation in the framework of Deep Learning that leverages learned weights. The formalism is described in detail providing both an accurate elucidation of the mechanics and the theoretical implications.
Code (by Curtó and Zarza):
Best regards,
De Curtó.

Advances in AI and Machine Learning: Addressing Risks and Concerns, IEEE Intl Workshop at COMPSAC, Madrid, July 2020 — CALL for PAPERS

 

Third IEEE International Workshop on
Advances in Artificial Intelligence and Machine Learning (AIML):

Addressing Risks and Concerns

 

Call for Papers and Participation

 

Submissions Due:  9 April 2020

https://ieeecompsac.computer.org/2020/aiml/

 

Artificial intelligence (AI) is finally starting to deliver real-world benefits, and early adopters in businesses and industry in several sectors are embracing the promise of AI reaping significant benefits. On the downside, like any new technology, AI presents risks, raises concerns regarding its safety and societal impact, and poses development and implementation challenges. To reap fuller potential of AI, we must satisfactorily address these shortcomings.

This 3rd IEEE International Workshop on Advances in AI and Machine Learning (AIML) aims to examine risks and concerns of AI and machine learning (ML) and showcase scientific, technical and practical advances in addressing them.  The workshop will also highlight recent advances in AI and ML and their applications, cover AI strategy and policy, examine development and deployment challenges, and discuss concepts such as AI for good, Responsible AI, and Explainable AI. It is an interactive forum for AI researchers, practitioners and business executives for discussion on key issues and challenges and practices related to AI applications, and for sharing case studies and application experience.

Researchers and practitioners from all over the world, from academia, industry, and government are invited to present their work, perspectives, experiences and vision, and participate in the workshop.

 

Topics of interest include, but are not limited to:

  • Advances in AI and machine learning, deep learning, cognitive computing, intelligent agents, chatbot
  • AI strategy for business and industry
  • AI applications in industry, business, healthcare, and education and training
  • AI in government and legal practice
  • Entertainment in the age of AI
  • AI for enhancing information security and privacy
  • Work in the age of AI
  • Trust, resilience, privacy and security issues in AI applications
  • Testing and validation of AI and ML applications
  • Risks, limitations, and challenges of AI and ML
  • Legal, regulatory, ethical aspects of AI (liability, etc.)
  • AI: promise vs practice
  • Societal implication of the rise of AI
  • Human-machine co-existence and collaboration
  • Intelligent, autonomous robots and cars
  • Industry 4.0
  • Smart society
  • AI and IoT
  • Case studies, experience reports, position papers and visionary perspectives
  • Overview of AI activities in a region/country
  • The Future of AI

 

Authors are invited to submit original, unpublished papers. 

 

Simultaneous submission to other publication venues is not permitted. In accordance with IEEE policy, submitted manuscripts will be checked for plagiarism; instances of alleged misconduct will be handled according to the IEEE Publication Services and Product Board Operations Manual.

 

For detailed instructions on submission see Information for Authors at https://ieeecompsac.computer.org/2020/.

 

Submissions Due: 9 April 2020

 

Workshop organizers

San Murugesan, Director BRITE Professional Services; Editor in Chief Emeritus,
IEEE CS IT Professional, Australia
, san1@internode.net

Yunji Liang, Northwestern Polytechnical University, P.R.China, liangyunji@nwpu.edu.cn

Piyush Saxena, Direct Supply, USA, piyush.saxena.phd@gmail.com

Lia Morra,  Politecnico di Torino, Italy,  lia.morra@polito.it

—————————–

Professor San Murugesan

Adjunct Professor, Western Sydney University

Director, BRITE Professional Services

Former Editor-in-Chief, IEEE IT Professional

Sydney, Australia

 

Website: http://tinyurl.com/sanbio

Email: san1@internode.net





CfP: Tools for Creating XR Media Experiences (Workshop in conjunction with ICME 2020)

First International Workshop on Tools for Creating XR Media Experiences
https://icme2020workshopxr.wordpress.com/

The workshop is held on July 6 in conjunction with IEEE ICME 2020 conference, 6-10 July 2020, London.
The keynote will be given by Professor Aljosa Smolic, Trinity College Dublin.

This workshop calls for original contributions on new approaches, technologies and tools for creating, processing and delivering interactive XR media (3D/CGI content/point clouds, 360° video, 3DoF+/6DoF video, volumetric video, spatial audio, .).

Topics of interest include, but are not limited to:
.       Efficient XR content acquisition and representation
.       Compression and delivery to various platforms (HMD, smartphones, SmartTV / HbbTV, Web, .)
.       Subjective and objective assessment of XR scenarios (content quality, experiences, .)
.       Semantic understanding of XR content (depth estimation, semantic segmentation, object recognition, pose estimation, action recognition, audio analysis, etc.)
.       Automating the XR content authoring process (e.g. providing automatic content annotation / storytelling)
.       Authoring interactions and navigation aids (e.g., elements for moving in time and space, avatars)
.       Authoring accessible XR experiences (e.g. subtitles, audio description, audio subtitling, sign language, .)

Important Dates:
Paper submission deadline: 13 March 2020 Notification of acceptance: 15 April 2020 Camera-ready paper due: 29 April 2020

For more information, see the website https://icme2020workshopxr.wordpress.com

IS&T Color & Imaging Conference (CIC28): CFP Open, Submit by April 26

Join us for a week of color 2-6 November 2020 in Chiba, Japan! The IS&T Twenty-eighth Color and Imaging Conference (CIC28) provides a wealth of ways to extend your network and the reach of your work with several opportunities to showcase your research through conference sessions, posters, Short Courses, workshops, and collocated events including IS&T's Printing for Fabrication Conference, DevCon2020, ICAI 2020, and MCS'20.
LEARN MORE: http://bit.ly/CIC28_

TOPICS:
Color Perception | Capture, Display, and Print | Material Appearance and Color | Color Theory | Image Quality | Color in Illumination and Lighting | Multispectral Imaging | Specific Color Applications

SUBMISSION OPTIONS:
Authors have the option to submit either a traditional conference paper https://www.openconf.org/CIC28/openconf.php  or Journal-first paper to either the Journal of Imaging Science and Technology (JIST) http://jist.msubmit.net/  or the Journal of Perceptual Imaging (JPI) http://jpi.msubmit.net/ .

DEADLINES:
*Journal-first: 1 April 2020
*Conference Paper: 26 April 2020
*Final Manuscript: 7 September 2020

SHORT COURSE CFP: http://bit.ly/IST_SCProposals The conference offers an extensive array of classes on 2-3 November taught by world-renowned experts, including the one-day intensive Color, Vision, and Basic Colorimetry.

Submit short course proposals by 1 March 2020.

WORKSHOP CFP:
Workshops occur the afternoon of Tuesday, 3 November and are scheduled for 2.5 hours. Email your proposal to color@imaging.org. Please put “CIC28 Workshop Proposal” and your last name in the subject line.

Submit workshop proposals by 1 April 2020.

View the Call for Papers for more information: http://bit.ly/CIC28_CFP

Direct submission inquiries to Katrina Bird @ cic-papers@imaging.org

Connect with our community!
Twitter @ImagingOrg #CIC28 https://twitter.com/ImagingOrg IS&T LinkedIn Groups: imaging.org, color and imaging (CIC), archiving (Archiving), & digital printing (Printing for Fabrication)

Call for papers to a Special Issue in Scalable Information Systems (WoS indexed) Journal

Web version
European Alliance for Innovation

Call for Papers

Special issue on "Intelligent Data Organization"
 
Manuscript submission deadline: March 7, 2020

Publication Opportunities
Papers will be published in 
EAI Endorsed Transactions on Scalable Information Systems
indexed in Web of Science, DOAJ, CrossRef, among others!
Submit paper
In order to submit, please select the journal and choose the special issue.
Scope & Topics

The smart usage of memory resources is more important every day, especially now that the new algorithms are requiring massive data processing. Data storage in main memory becomes more essential than ever. Integration of different memory units in the computational architecture, smart distribution of emerging memory modules  and usage of smart system algorithms are developed to take advantages of  such new organization; this  is challenging and requires more study as the new application demands faster access to the stored data, so the response of the applications can be done in real-time (read more).

We welcome contributions from the following topics:

  • Data storage management,
  • Emerging memory resources,
  • New computational architectures
  • Smart system software
Guest editors

Dr. Alberto Arteta – Troy University, USA

Dr. Luis Fernando Mingo – Polytechnic University of Madrid, Spain

This issue will be published in EAI Endorsed Transactions on Scalable Information Systems an open-access, peer-reviewed journal abstracted/indexed in Web of Science, DOAJ, CrossRef, OCLC, among others. It focuses on scalable distributed information system, scalable, data mining, grid information systems and more. The journal publishes research articles, review articles and editorials with a quarterly frequency. Authors are not charged for article submission and processing.

Important dates

Manuscript submission deadline: March 7, 2020

Notification of acceptance:  April 7, 2020

Submission of final revised paper: May 8, 2020

Publication of special issue (tentative): June 19, 2020

Community Benefits
Granting you visibility and fair review through Community Review.
Credits counting towards your EAI Index, membership ranks and global recognition.
Fast Proactive Publication process (EAI Transactions).

follow us!

facebook You Tube twitter
Unsubscribe
Share:

Design by 2b Consult