Related papers: Representation Learning of Daily Movement Data Usi…

Interactive adaptive systems powered by Reinforcement Learning (RL) have many potential applications, such as intelligent tutoring systems. In such systems there is typically an external human system designer that is creating, monitoring…

Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an efficient representation space that is invariant under…

Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using…

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…

Speaker individuality information is among the most critical elements within speech signals. By thoroughly and accurately modeling this information, it can be utilized in various intelligent speech applications, such as speaker recognition,…

The gesture recognition using motion capture data and depth sensors has recently drawn more attention in vision recognition. Currently most systems only classify dataset with a couple of dozens different actions. Moreover, feature…

Learning structured task representations from human demonstrations is essential for understanding long-horizon manipulation behaviors, particularly in bimanual settings where action ordering, object involvement, and interaction geometry can…

Clinical notes are a rich source of information about patient state. However, using them to predict clinical events with machine learning models is challenging. They are very high dimensional, sparse and have complex structure. Furthermore,…

As the number of dementia patients rises, the need for accurate diagnostic procedures rises as well. Current methods, like using an MRI scan, rely on human input, which can be inaccurate. However, the decision logic behind machine learning…

Electroencephalography (EEG) decoding is a challenging task due to the limited availability of labelled data. While transfer learning is a promising technique to address this challenge, it assumes that transferable data domains and task are…

A fundamental challenge in neuroscience is to decode mental states from brain activity. While functional magnetic resonance imaging (fMRI) offers a non-invasive approach to capture brain-wide neural dynamics with high spatial precision,…

Multimodal representation learning has demonstrated remarkable potential in enabling models to process and integrate diverse data modalities, such as text and images, for improved understanding and performance. While the medical domain can…

Human activity recognition (HAR) research has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with…

Texts from scene images typically consist of several characters and exhibit a characteristic sequence structure. Existing methods capture the structure with the sequence-to-sequence models by an encoder to have the visual representations…

Network-structured data becomes ubiquitous in daily life and is growing at a rapid pace. It presents great challenges to feature engineering due to the high non-linearity and sparsity of the data. The local and global structure of the…

Effective dementia caregiving requires training and adaptive communication, but assistive AI and robotics are constrained by a lack of context-rich, privacy-sensitive data on how people living with Alzheimer's disease and related dementias…

We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts,…

Learning effective representations of visual data that generalize to a variety of downstream tasks has been a long quest for computer vision. Most representation learning approaches rely solely on visual data such as images or videos. In…

While deep learning has revolutionized research and applications in NLP and computer vision, this has not yet been the case for behavioral modeling and behavioral health applications. This is because the domain's datasets are smaller, have…

Understanding and reasoning about places and their relationships are critical for many applications. Places are traditionally curated by a small group of people as place gazetteers and are represented by an ID with spatial extent, category,…