Programme is available on-line

Background

Machine learning builds models of the world using training data from the application domain and prior knowledge about the problem. The models are later applied to future data in order to estimate the current state of the world. An implied assumption is that the future is stochastically similar to the past. The approach fails when the system encounters situations that are not anticipated from the past experience. In contrast, successful natural organisms identify new unanticipated stimuli and situations and frequently generate appropriate responses.
This workshop aims to discuss moving the art of machine recognition from the classical signal processing/pattern classification paradigm to human-like information extraction.
This means, among other things, to move from interpretation of all incoming data to reliable rejection of non-informative inputs, from passive acquisition of a single incoming stream to active search for the most relevant information in multiple streams, and from a system optimized for one static environment to autonomous adaptation to new changing environments, thus forming the foundation for a new generation of efficient cognitive information processing technologies.

Aims and Scope

The workshop aims to bring together researchers and students from different disciplines (machine learning, data mining, pattern recognition, computer vision, speech processing, neurophysiology, psychophysics, robotics, …) in order to present and discuss in an informal atmosphere new approaches for identifying and reacting to unexpected events in information-rich environments. To achieve this goal we are soliciting two types of contributions: a) mature research results, and b) interesting preliminary results or stimulating position statements. In addition, the workshop will feature at least one discussion session to allow for a more interactive and engaging experience.

Topics of Interest

The workshop's topics of interest include (but are not limited to):

• learning from small samples
• unusual/abnormal event detection
• trend analysis
• novelty detection
• classification-based/clustering-based/nearest neighbor based/statistical/information theoretical /spectral/ ...
• contextual anomaly detection
• audio-visual perception of humans
• human-computer interaction modeling
• speech processing
• image and video processing
• multimodal processing, fusion and fission
• multimodal indexing, structuring and summarization
• annotation and browsing of multimodal data
• machine learning algorithms and their applications to the topics above