NTENT’s Head of Machine Learning to Participate at the International Conference on Machine Learning (ICML 2019)
NTENT’s Head of Machine Learning, Stefanos Poulis, will be participating at the 36th International Conference on Machine (ICML 2019) in Long Beach, CA (June 9–15, 2019). Poulis, along with co-authors, will be presenting two research papers at this year’s conference.
The first paper, titled “Teaching a Black-Box Learner”, focuses on an area of machine learning called “machine teaching”. The paper considers the problem of how a “Teacher” (e.g. a human or a machine) can communicate a concept to a “Learner” (e.g. another machine) concisely. This is of interest in the field of conversational AI when teaching a new skill such as “ordering pizza”, “playing music”, etc. to a virtual assistant through examples. The central question that the paper addresses is how many teaching examples does the “Teacher” need to come up with to communicate a particular skill. The paper gives a protocol that allows teaching without too many examples, even when the “Learner” is a black box, such as a deep neural network.
The second paper, titled “Interactive Topic Modeling with Anchor Words”, focuses on an area of unsupervised machine learning called “topic modeling” and will be presented at the Workshop on Human In the Loop Learning (HILL). Topic models are typically used for organizing large collections of documents into topics, for example when wanting to categorize news articles into coherent themes such as sports, politics, entertainment, etc. The paper gives an interactive protocol that allows users to build customized and interpretable topic models.
The HILL workshop brings together researchers and practitioners who study interpretable and interactive learning systems with applications in large scale data processing, data annotations, data visualization, human-assisted data integration, systems and tools to interpret machine learning models as well as algorithm designs for active learning, online learning, and interpretable machine learning algorithms. The target audience for the workshop includes people who are interested in using machines to solve problems by having a human be an integral part of the process.
ICML will begin on Sunday June 9th with a full day industry exposition consisting of talks, panels, demonstrations and workshops presented by ICML sponsors. Most of the content at ICML 2019 will be live streamed. Please visit www.icml.cc for details.
NTENT provides Search and Conversational AI Platforms, empowering our partners to add search and conversational intelligence to anything. Maintain your data and direct relationships with your customers when you customize, localize and integrate our search, natural language understanding, and Q&A technologies directly into your lines of business.
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML will host over 8,000 participants. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.