CSDL 2016 - Symposium on Compressed Sensing, Deep Learning

The IEEE Global Conference on Signal and Information Processing (GlobalSIP) is the flagship conference of the IEEE Signal Processing Society. GlobalSIP 2016 will be held in Washington, DC, USA, December 7-9, 2016. The conference will focus broadly on signal and information processing with an emphasis on up-and-coming signal processing themes.
The Sparse Signal Processing and Deep Learning symposium will explore deep connection between sparsity of signals and deep learning theory , and will thus focus on novel signal processing ideas and results, both experimental and theoretical, in learning compact and meaningful signal representations, in efficient signal sampling and sensing, and in computational methods for high-dimensional big data sets that pervade the current information age.
Submissions are welcome on topics including:
Connections between sparse auto encoders and sparse representationSparse coding, sparse representations, and dictionary learningSparse and low-rank approximation algorithmsLearning on graphsConnections between learning rate and sampling rateSparsity and super resolution.Recurrent neural networks for periodic and quasi-periodic signalsPhase retrieval and bilinear problemsTensor sketching and factorizationsCompressed learning ? compressive sensing for learning: new theory and methodsDimensionality reduction, feature extraction, classification, detection, and source separationGeometric wavelet theorySparsity measures in approximation theory, information theory and statisticsRegularization theory with low-complexity / low-dimensional structuresStatistical models and algorithms for sparsitySparse network theory and analysisEnd-to-end deep-learning pattern recognition systemsAdvanced supervised and unsupervised deep-learning algorithmsDeep-learning software and hardware architectureBig data applications