Extracting meaning from data


Extracting meaning from data is the central business of the information era. ML Market is a European consortium of leading researchers that span a range of areas in information processing, data analysis, statistics and machine learning.

ML Market groups are formed from world-leading research groups within the Pascal European network that also actively engage to find business solutions to challenging real-world problems. ML Market exists to promote the academic and industrial expertise of its researchers and provides a platform to engage and broker industrial contacts.

Case Studies

Letting stones go unturned

Wéiqí, Baduk or simply, Go. Over two thousand years old, this challenging game of strategy and tactics has taught warriors, monks and intellectuals to focus, concentrate and plan. But a program is beginning to change our views of what is possible. In computer competitions this multi-armed bandit has stolen first prize more often than any other. It’s MoGo, or Monte Carlo Go.

Financial Prediction

Gaining wealth on the stock market based on statistical arbitrage is an area ripe for the application of machine learning and related methods. UCL's clients include large financial organisations that require state of the art prediction methods based on both low to high frequency trading. UCL has developed state of the art prediction methods that track market dynamics which translate into profitable portfolio allocations. Success in this area demands an understanding of the underlying dynamics of the statistics underlying markets, and also when these dynamics changes.

Bonaparte Disaster Victim Identification System

Society is increasingly aware of the possibility of a mass disaster. Recent examples are the WTC attacks, the tsunamis, and various airplane crashes. In such an event, the recovery and identification of the remains of the victims is of great importance, both for humanitarian as well as legal reasons. Disaster victim identification (DVI), i.e. the identification of victims of a mass disaster, is greatly facilitated by the advent of modern DNA technology. In forensic laboratories, DNA profiles can be recorded from small samples of body remains which may otherwise be unidentifiable.


Interactive Natural Language Processing

KeyboardThe current state of the art in different areas of natural language processing (NLP) is very far from allowing fully automatic high quality results (HQRs), therefore human intervention is required to correct the output of the NLP engines. This applies specifically to NLP fields such as: machine translation and cross-language processing, text recognition, parsing, speech recognition, information retrieval, etc.

Its goal is to produce HQRs through a tight collaboration between a human operator and a NLP system, following an interactive-predictive paradigm. On the other hand, interactivity offers a unique context in which the feedback provided by the human can be used as new training data for adapting the NLP systems to new environments.

Time Series Analysis

Timeseries appear in a variety of disciples, from finance to physics, computer science to biology. The origins of the subject and diverse applications in the engineering and physics literature at times obscure the commonalities in the underlying models and techniques. Modern timeseries applications include financial timeseries prediction, video-tracking, music analysis, control theory and genetic sequence analysis.

Multimodal Interaction and Adaptive Learning

Traditional Pattern Recognition (PR) and Machine Learning (ML) have generally focused on full automation; that is, in developing technologies ultimately aiming at fully replacing human beings in tasks that require complex perceptive and/or cognitive skills. However, full automation often proves elusive or unnatural in many applications where technology is expected to assist rather than replace the human agents. This asks for a paradigm shift which should place PR/ML within the framework of human interaction.

Multimodal Interaction and Adaptive Learning deals with the fundamental work needed to address the research challenges and opportunities entailed by this paradigm shift. These include: interaction analysis and modelling, multimodal processing and fusion, interactive performance estimation and measurement, and several emerging forms of machine learning that look especially promising in the interactive framework (online, adaptive, active, semi-supervised, limited feedback, reinforcement, etc.).