-
1
Tensor factorization for missing data imputation in medical questionnaires
Published 2013“…Measures such as normalized root mean square error, bias and variance are used to assess the performance of the proposed tensor-based methods in comparison with other widely used approaches, such as mean substitution, regression imputations and k-nearest neighbor estimation. …”
Get full text
Get full text
Conference Paper -
2
Multi-channel EEG compression based on matrix and tensor decompositions
Published 2013“…Compression schemes for EEG signals are developed based on matrix and tensor decomposition. Various ways to arrange EEG signals into matrices and tensors are explored, and several matrix and tensor decomposition schemes are applied, including SVD, CUR, PARAFAC, the Tucker decomposition, and recent random fiber selection approaches. …”
Get full text
Get full text
Conference Paper -
3
Tensor decomposition based R-dimensional matrix pencil method
Published 2012“…Furthermore, it is straightforward to extend the proposed R-D tensor MP to other MP type methods, such as R-D unitary tensor MP, R-D beamspace tensor MP.…”
Get full text
Get full text
Get full text
Conference Paper -
4
Multi-channel EEG compression based on 3D decompositions
Published 2013“…The multi-channel EEG is represented as a three-way tensor (or 3D volume) to exploit both spatial and temporal correlations efficiently. …”
Get full text
Get full text
Conference Paper -
5
DNN model theft through trojan side-channel on edge FPGA accelerator
Published 2024“…In particular, our attack targets the widely-used Versatile Tensor Accelerator (VTA). A hardware trojan is employed to track the memory transactions by monitoring the AXI interface signals of VTA’s submodules. …”
Get full text
Conference Paper -
6
Streamlining DNN obfuscation to defend against model stealing attacks
Published 2024“…However, state-of-the-art (SOTA) DNN obfuscation is time-consuming, requires expertlevel changes in existing DNN compilers (e.g., Tensor Virtual Machine (TVM)), and often relies on prior knowledge of the attack models. …”
Get full text
Get full text
Conference Paper -
7
Out of distribution reasoning by weakly-supervised disentangled logic variational autoencoder
Published 2024“…Our framework consists of three steps: partitioning data based on observed generative factors, training a VAE as a logic tensor network that satisfies disentanglement rules, and run-time OOD reasoning. …”
Get full text
Conference Paper