Machine Learning

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

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 College Dublin. We published the implementation and pre-print only a few days ago, and have received considerable interest Read more…

By Mark Collier, ago
Machine Learning

Teaching

All lecture materials (lecture slides, assignments, exams) and the latest news are available on  Machine Learning (CS7CS4/CS4404) Students who complete this module should be able to (1) Decide when machine learning is an appropriate method to solve a problem (2) Understand how machine learning works. (3) Apply machine-learning frameworks to solve real-world problems, and adjust and extend existing algorithms when necessary. The module content includes Machine Learning Basics (Application Areas, Challenges, Alternatives to Machine Learning) Machine Learning in Action (Datasets, Frameworks, Evaluation) Cross-validation and confidence intervals Overfitting/underfitting (bias-variance trade-off) Machine Learning Algorithms Linear Regression Logistic Regression Support Vector Machines Kernel Methods k-Means Clustering and Mixture Models for Unsupervised Learning Neural Networks Deep Learning Algorithms Use of gradient descent, and extensions for Read more…

By Joeran Beel, ago
Machine Learning

Aiur by Iris.ai: Solving the Problems of Science via the Blockchain and Artificial Intelligence

I am on the advisory board of Iris.ai, a business start-up in the field of open science, blockchain, and artificial intelligence. Iris.ai was founded in 2015 and since then has released several exciting products that have the potential to revolutionize how scientists work. With their latest project, Project Aiur, the team behind Iris.ai envisions a world where the right scientific knowledge is available at our fingertips; where all research is validated and reproducible; where interdisciplinary connections are the norm; where unbiased scientific information flows freely; where research already paid for with our tax money is freely accessible to all. To realize Project Aiur, Iris.ai sells “AIUR tokens”, a new currency that could be the central currency in a new world of Read more…

By Joeran Beel, ago
Machine Learning

DAAD Artificial Intelligence / Machine Learning Tour Through Germany for Postdocs from Outside Germany

The German Academic Exchange Service (DAAD) organizes the “Postdoctoral Researchers’ Networking AI Tour” 2018 to offer on-site visits to universities, research institutes and companies in the field of artificial intelligence, discussions with experts and numerous networking opportunities. Programme-related costs and a travel allowance are covered by DAAD. We have cooperated and received funding from the DAAD on numerous occasions, e.g. to participate in conferences, receive interns, or conduct research visits abroad e.g. in Cyprus and Tokyo. We were always pleased by the professional organization of DAAD events and great networking opportunities that DAAD offered. As such, we can highly recommend applying for the DAAD Artificial Intelligence Tour through Germany, if you are a postdoc from outside Germany who considers working and living Read more…

By Joeran Beel, ago
Machine Learning

Call for Marie Curie Individual Fellowships: We are open to supervise projects relating to recommender-systems, machine learning, and NLP here at TCD Dublin

The European Union has published the call for Individual Marie Curie Fellowships (MSCA) with the application deadline being 12 September 2018. The goal of the Individual Fellowships is to enhance the creative and innovative potential of experienced researchers. Our group has already one Marie Curie fellow, i.e. a postdoctoral researcher, as part of the EU/SFI EDGE fellowship programme. However, we are open to supervise more postdoctoral researchers. If you are interested in applying for the Individual Marie Curie Fellowship and need a supervisor, please contact us. We are particularly interested in projects relating to machine learning (machine translation, machine-learning evaluation, novel machine-learning algorithms, curriculum learning), recommender systems, and natural language processing.

By Joeran Beel, ago
Jobs & Internships

We are hiring (again): Software Engineer / Machine-Learning Engineer / Software Architect / Product Manager for a Recommender-Systems Spin-Out Company (TCD Dublin, Ireland)

We have received funding to hire two employees to spin-out a business start-up in the field of recommendations-as-a-service. The two positions are to be filled with two machine-learning engineers, software engineers, software architects or product managers and both employees are expected to work together very closely here at Trinity College Dublin, the ADAPT Centre respectively. The employees will be responsible for developing a recommender-system as-a-service that uses a unique machine-learning technology, which is based on the research of Asst. Professor Joeran Beel who is the project lead. The first position is already filled with a full-stack software engineer and software architect. This person is flexible in the responsibilities and open to focus more on either the software engineering / machine-learning Read more…

By Joeran Beel, ago
Machine Learning

We will present at the next Machine Learning Dublin (Ireland) Meetup @Zalando

The next Machine Learning Dublin Meetup will take place on 30th April 2018 at Zalando Dublin, 3 Grand Canal Quay, Dublin 2, Ireland from 6:00 PM to 9:00 PM. I am one of the three presenters: Joeran Beel, Assistant Professor at ADAPT Centre The Potential of Meta Recommender-Systems at Macro- and Micro Level We introduce the concept of “macro” and “micro” recommender systems. Both systems can be considered as meta recommender systems for recommendation algorithms. A macro recommender system recommends the potentially best performing recommendation algorithm to an organization that wants to build a recommender system. This way, an organization does not need to test dozens or even more algorithms to find the best one for their particular platform. A micro Read more…

By Joeran Beel, ago
Machine Learning

New domain name for our website: machine-learning.ie

We successfully registered the domain machine-learning.ie (in addition to our domain names relating to recommender-systems). For now, all domains point to our main website https://www.scss.tcd.ie/joeran.beel/. In the long run, we may use the domain machine-learning.ie for more specific purposes relating to machine learning. For instance, we may build a platform that provides an overview of all research and development activities going on in Dublin and Ireland relating to machine learning. This could include a list of machine-learning researchers, machine-learning research-centres, machine-learning meetups, and machine-learning business start-ups. If you are interested in building and maintaining such a list, please contact us.  

By Joeran Beel, ago
Conferences

AICS’2018: We Co-Organize the 26th Irish Conference on Artificial Intelligence and Cognitive Science

We are delighted to announce the 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS’2018), which we will co-organize together with Rob Brennan, Ruth Byrne, Jeremy Debattista, and a renowned program committee. AICS 2018 takes place from December 6 to 7, 2018 at Trinity College Dublin, more precisely in the Long Room Hub. Deadline for submissions is 30th September 2018. There will be three tracks for submissions, namely full papers, NECTAR Papers, and student papers. The call for papers invites papers relating particularly to machine learning, machine translation, neural networks, data mining, cognitive modelling, behaviour epistemology, evolutionary computation, recommender systems, collective intelligence, human learning, and several more. AICS 2018 is sponsored by the ADAPT Research Centre, Trinity Long Room Hub, and Trinity College Dublin. AICS dates Read more…

By Joeran Beel, ago
Machine Learning

Machine Learning Meetup at DogPatch — 26th March

The Machine Learning Meetup in Dublin, takes place on the last Monday every month. This month, the machine learning meetup is hosted by Dogpatch and there will be plenty of exciting presentations about machine learning: Marco Forte (PhD researcher, Sigmedia Group) speaks about foreground estimation in machine learning and motion estimation for video matting in machine learning including deep learning techniques to create more consistent and content-aware results. Procheta Sen (PhD researcher, ADAPT Centre) speaks about cross-session search and tempo-lexical context-driven machine-learned word embeddings. Elias Giacoumidis, (Marie-Curie Fellow, CONNECT) speaks about machine learning optical fiber telecommunications. The next machine learning meetup takes place on 26th March at The Vaults – Dogpatch Labs CHQ Building, Custom House Quay, Dublin. Talks are from 18:30 Read more…

By Joeran Beel, ago