DL 2018 - Workshop: “Deep Learning and Tensor/Matrix Decomposition for Applications in Neuroscience”

The workshop is oriented to all potential applications of deep learning and matrix/tensor decomposition and networks in feature extraction, classification, recognition, segmentation, enhancing, clustering, anomaly detection, and prediction of brain and behavior data – as applied to the multi-modal brain data (MRI/fMRI/CT, EEG/MEG, and biomarker assays), especially for mental disorders. Special focus will be made on the practical aspects of how to design and train deep neural networks with appropriate reduction of the dimensionality, to achieve high classification performance and reliability.
Because of recent breakthroughs in machine learning, especially deep neural networks, it is expected that physicians will be able to completely rely on the machine interpretation of MRIs, CT, PET scans using deep learning in the nearest future. Though deep neural networks have revolutionized computer vision through the end-to-end learning (i.e., learning from the raw data), it is still difficult to accomplish the early detection of the major neurodegenerative diseases (such as ADHD, Autism, or Alzheimer’s) with the neural networks today, partially due to the need for development of optimization techniques in order to work with the Big Data in the most efficient way. These and related topics will be addressed at this workshop.
Call for Papers
We aim for a focus on the applications of Deep Learning to analysis of neuroimaging data. Topics of interests for the workshop include, but are not limited to:
Magnetic Resonance Imaging (MRI) / functional Magnetic Resonance Imaging (fMRI)
Electroencephalography (EEG)
Magnetoencephalography (MEG)
Positron Emission Tomography (PET)
Near-infrared spectroscopy (NIRS)
Computed Tomography (CT)
Behavioral Data
Physiological Data
Electromyography (EMG)