2013 Proceeding
Intelligent systems or robots that interact with their environment by perceiving, acting or communicating often face a challenge in how to bring these different concepts together. One of the main reasons for this challenge is the fact that the core concepts in perception, action and communication are typically studied by different communities: the computer vision, robotics and natural language processing communities, among others, without much interchange between them. Learning systems that encompass perception, action and communication in a unified and principled way are still rare. As machine learning lies at the core of these communities, it can act as a unifying factor in bringing the communities closer together. Unifying these communities is highly important for understanding how state-of-the-art approaches from different disciplines can be combined (and applied) to form generally interactive intelligent systems.
MLIS-2013 aims to bring researchers from multiple disciplines together that are in some way or another affected by the gap between perception, action and communication. Our goal is to provide a forum for interdisciplinary discussion that allows researchers to look at their work from new perspectives that go beyond their core community and develop new interdisciplinary collaborations.
Proceeding Downloads
Learning machines that perceive, act and communicate
Humans are very good in perceiving all kinds of high-dimensional sensory inputs, extracting the meaningful information and acting on that information to pursue their goals. Having this in mind, our vision is a learning system, that takes raw, ...
Transfer learning with applications on text, sensors and images
Transfer learning has attracted increasing attention in machine learning, data mining, and many application areas. It is well-known that features sampled from different domains may differ tremendously in their distributions, or that labels across ...
Robots, skills, and symbols
This extended abstract summarizes recent work on skill acquisition, which shows that autonomous robot skill acquisition is feasible, and that a robot can thereby improve its own problem-solving capabilities; and on the symbolic representation of plans ...
Developmental robotics at Aldebaran A-Lab
Aldebaran Robotics is launching a developmental robotics activity as part of the new A-Lab research entity. The focus will be fundamental research and the scope of interest will range from low level categorization of sensorimotor information, up to high ...
Open knowledge for human-robot interaction
In indoor applications, a service robot is required to be able to understand and complete an open-ended set of user tasks. In this case, the designer cannot predict all user tasks, all variants of environment, or what knowledge will be needed in order ...
Machine learning for interactive systems and robots: a brief introduction
Research on interactive systems and robots, i.e. interactive machines that perceive, act and communicate, has applied a multitude of different machine learning frameworks in recent years, many of which are based on a form of reinforcement learning (RL). ...
Expectation propagation learning of finite Beta-Liouville mixtures for spatio-temporal object recognition
In this paper, we develop an efficient approach for the learning of finite Beta-Liouville mixture models. Unlike existing approaches, our is based on expectation propagation for parameters estimation and can select automatically the appropriate number ...
Homogeneity analysis for object-action relation reasoning in kitchen scenarios
Modeling and learning object-action relations has been an active topic of robotic study since it can enable an agent to discover manipulation knowledge from empirical data, based on which, for instance, the effects of different actions on an unseen ...
Shared control of a robot using EEG-based feedback signals
In the last years there has been an increasing interest on using human feedback during robot operation to incorporate non-expert human expertise while learning complex tasks. Most work has considered reinforcement learning frameworks were human feedback,...
Automatic interface optimization through random exploration of available elements
- Leonardo Anjoletto Ferreira,
- Andrey Araujo Masiero,
- Plinio Thomaz Aquino,
- Reinaldo Augusto da Costa Bianchi
The Keystroke-Level Model (KLM) is an interface evaluation method that use as metric the time needed to perform an executed action to complete a given task. The description used in KLM is very similar to the formalism that Markov Decision Process (MDP) ...
Social signal and user adaptation in reinforcement learning-based dialogue management
This paper investigates the conditions under which cues from social signals can be used for user adaptation (or user tracking) of a learning agent. In this work we consider the case of the Reinforcement Learning (RL) of a dialogue management module. ...
Inverse reinforcement learning for interactive systems
Human machine interaction is a field where machine learning is present at almost any level, from human activity recognition to natural language generation. The interaction manager is probably one of the latest components of an interactive system that ...
Index Terms
- Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication
Recommendations
Bridging the gap: voices from industry and research on industrial relevance of SPLC
SPLC '21: Proceedings of the 25th ACM International Systems and Software Product Line Conference - Volume AProduct line engineering emerged from a fruitful interaction of applied research in academia, industry research, and software engineering practice. SPLC was created as the primary venue to exchange ideas on this emerging topic and integrate the ...
Acceptance Rates
| Year | Submitted | Accepted | Rate |
|---|---|---|---|
| MLIS '13 | 14 | 10 | 71% |
| Overall | 14 | 10 | 71% |