Blog

Machine Learning

Best-Paper Award for our Publication “Implementing Neural Turing Machines” at the 27th International Conference on Artificial Neural Networks

We received the best-paper award at the 27th International Conference on Artificial Neural Networks (ICANN 2018) for our paper Implementing Neural Turing Machines. Our student, and co-author of the paper, Mark Collier was at ICANN to present the work. Neural Turing Machines (NTMs) are an instance of Memory Augmented Neural Networks, a new class of recurrent neural networks which decouple computation from memory by introducing an external memory unit. NTMs have demonstrated superior performance over Long Short-Term Memory Cells in several sequence learning tasks. A number of open source implementations of NTMs exist but are unstable during training and/or fail to replicate the reported performance of NTMs. This paper presents the details of our successful implementation of a NTM. Our implementation learns Read more…

Recommender Systems

Report/Photos from the 12th ACM Conference on Recommender Systems in Vancouver

Today, the 12th ACM Conference on Recommender Systems began in Vancouver, Canada. We attend and will present our work on meta-learning reference parsing tools in which we treat reference extraction from scientific articles as a recommendation problem. If you also attend the conference, visit us during the poster session on Thursday. So far, it has been a great conference with many exciting talks. A few of the many great presentations are the following Why I like it: Multi-task Learning for Recommendation and Explanation We describe a novel, multi-task recommendation model, which jointly learns to perform rating prediction and recommendation explanation by combining matrix factorization, for rating prediction, and adversarial sequence to sequence learning for explanation generation. The result is evaluated using real-world Read more…

Machine Learning

An Empirical Comparison of Syllabuses for Curriculum Learning (Pre-Print)

We have published a pre-print (now available on Arxiv) which outlines our work comparing different syllabuses for curriculum learning. Neural networks are typically trained by repeatedly randomly selecting examples from a dataset and taking steps of stochastic gradient descent. Curriculum learning is an alternative approach to training neural networks, inspired by human learning in which training examples are presented according to a syllabus typically of increasing “difficulty”. Curriculum learning has shown some impressive empirical results, but little is known about the relative merits of different syllabuses. In this work we provide an empirical comparison of a number of syllabuses found in the literature. Abstract Syllabuses for curriculum learning have been developed on an ad-hoc, per task basis and little is Read more…

Jobs & Internships

Open Call for “Government of Ireland Postgraduate Scholarship Programme 2019”

The Irish Research Council (IRC) has published a new call for its “Government of Ireland Postgraduate Scholarship” programme. We are eligible to supervise applicants during their application process and act as PhD supervisor for the 4-year period of the scholarship. Hence, if you are interested in doing a PhD at Trinity College Dublin in the field of machine learning or recommender systems, or any other of our research fields, please contact us. From their website The Government of Ireland Postgraduate Scholarship Programme is an established national initiative, funded by the Department of Education and Skills and managed by the Council. In 2017, we invested in a total of 1,179 postgraduate scholars, with over 5,000 individual scholarships for excellent research awarded Read more…

Machine Learning

3rd Call for EU Marie Curie EDGE Fellowships (e.g. in Machine-Learning or Recommender-Systems Research)

The 3rd call for EU Marie Curie EDGE fellowships has been published. We successfully supported the application of one EDGE fellow a year ago, and we would be happy to support talented candidates this year, too. So, if you are interested in an EDGE fellowship in the field of machine learning, recommender systems or another of our research areas, please contact us. Let us know some details about your yourself and your project idea. EDGE is Marie Skłodowska-Curie COFUND Action, led by Trinity College Dublin on behalf of a group of academic institutions from across Ireland. EDGE will offer 71 prestigious Fellowships for experienced researchers (post-doctoral or equivalent) relocating to Ireland. EDGE is also a training and development programme for scientific excellence, offering a Read more…

Machine Learning

Trinity College Dublin seeks to hire a Professor (Chair) in Intelligent Systems

The University of Dublin, Trinity College, invites applications for the position of Professor of Intelligent Systems. The successful candidate will provide strong academic leadership in research, teaching and supervision. The Professor will strengthen the strategic research areas of Artificial Intelligence and Intelligent Content in the School of Computer Science and Statistics, and provide additional leadership in the SFI Research Centre for Digital Content Technology – ADAPT (www.adaptcentre.ie), hosted in the School. It is essential that the successful candidate will be an internationally recognized scholar in at least one of the following research areas: artificial intelligence; digital media and content analytics; knowledge and data engineering. These areas include scientific areas such as: Machine Learning; Natural Language Processing; Semantic Modelling; Personalisation; Data Read more…

Machine Learning

ParsRec: Meta-Learning Recommendations for Bibliographic Reference Parsing (Pre-Print)

We are delighted to announce that our poster “ParsRec: Meta-Learning Recommendations for Bibliographic Reference Parsing” has been accepted at the 12th ACM Recommender Systems Conference (RecSys) for presentation in Vancouver, Canada. The pre-print is available on arXiv, and here in our blog: Abstract Bibliographic reference parsers extract metadata (e.g. author names, title, year) from bibliographic reference strings. No reference parser consistently gives the best results in every scenario. For instance, one tool may be best in extracting titles, and another tool in extracting author names. In this paper, we address the problem of reference parsing from a recommender-systems perspective. We propose ParsRec, a meta-learning approach that recommends the potentially best parser(s) for a given reference string. We evaluate ParsRec on 105k Read more…

Machine Learning

A Stable Neural-Turing-Machine (NTM) Implementation (Source Code and Pre-Print)

Update 2018-10-20: Official publication available at SpringerLink Update: 2018-10-06: Our paper received the best-paper award at ICANN.   We have released an open source implementation of a Neural Turing Machine for TensorFlow, and published on arXiv the corresponding paper which we will present at ICANN 2018. Neural Turing Machines are notoriously difficult to implement and train. Our contribution is to explain why previous implementations have not successfully replicated the results in the original Neural Turing Machines paper. We then went on and produced an open source implementation which trains reliably and quickly. The work was done as part of my undergraduate thesis in the group of Prof Joeran Beel at the School of Computer Science and Statistics and the ADAPT Centre at Trinity Read more…

Recommender Systems

Mr. DLib’s Living Lab for Scholarly Recommendations (preprint)

We published a manuscript on arXiv about the first living lab for scholarly recommender systems. This lab allows recommender-system researchers to conduct online evaluations of their novel algorithms for scholarly recommendations, i.e., research papers, citations, conferences, research grants etc. Recommendations are delivered through the living lab´s API in platforms such as reference management software and digital libraries. The living lab is built on top of the recommender system as-a-service Mr. DLib. Current partners are the reference management software JabRef and the CORE research team. We present the architecture of Mr. DLib’s living lab as well as usage statistics on the first ten months of operating it. During this time, 970,517 recommendations were delivered with a mean click-through rate of 0.22%. Read more…

Recommender Systems

RARD II: The 2nd Related-Article Recommendation Dataset (preprint)

We released a new version of RARD, i.e. RARD II and describe the new release in a preprint published on arXiv. The dataset is available at http://data.mr-dlib.org and the new manuscript is available on arXiv and here in our Blog. The main contribution of this paper is to introduce and describe a new recommender-systems dataset (RARD II). It is based on data from a recommender-system in the digital library and reference management software domain. As such, it complements datasets from other domains such as books, movies, and music. The RARD II dataset encompasses 89m recommendations, covering an item-space of 24m unique items. RARD II provides a range of rich recommendation data, beyond conventional ratings. For example, in addition to the usual rating Read more…

Partnerships

2-week visit at the NII Tokyo: Dagstuhl-Seminar Presentation, Recommender-System and Machine-Learning Research, …

From the 19th of June until the 2nd of July 2018, I am in Japan at the National Institute of Informatics (NII). It is my first visit as Visiting Professor at the NII, and I am working with Professor Akiko Aizawa on a recommender-system and machine-learning project. Besides that work, there are many interesting presentations and other visitors at the NII. Among others, Prof. Dr. Raimund Seidel is visiting. Prof. Seidel is the organizer of the prestigious Dagstuhl seminar. Dagstuhl enables leading researchers in computer science meet for a few days to discuss the latest advancements and challenges in their fields. The NII is organizing a similar seminar series, the Shonan seminars, and Prof. Seidel shared his experience with organizing the Dagstuhl in a Read more…