J
Jayaraman J. Thiagarajan
Researcher at Lawrence Livermore National Laboratory
Publications - 253
Citations - 2977
Jayaraman J. Thiagarajan is an academic researcher from Lawrence Livermore National Laboratory. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 24, co-authored 221 publications receiving 2179 citations. Previous affiliations of Jayaraman J. Thiagarajan include Arizona State University & Arizona's Public Universities.
Papers
More filters
Proceedings Article
Attend and diagnose: Clinical time series analysis using attention models
TL;DR: In this paper, a self-attention mechanism is employed for clinical time-series modeling, which employs a masked, self attention mechanism, and uses positional encoding and dense interpolation strategies for incorporating temporal order.
Proceedings ArticleDOI
Sparse representations for automatic target classification in SAR images
Jayaraman J. Thiagarajan,Karthikeyan Natesan Ramamurthy,Peter Knee,Andreas Spanias,Visar Berisha +4 more
TL;DR: Results show that the performance of the algorithm is superior to using a support vector machines based approach with similar assumptions, and significant complexity reduction is obtained by reducing the dimensions of the data using random projections for only a small loss in performance.
Journal ArticleDOI
Visual Exploration of Semantic Relationships in Neural Word Embeddings
Shusen Liu,Peer-Timo Bremer,Jayaraman J. Thiagarajan,Vivek Srikumar,Bei Wang,Yarden Livnat,Valerio Pascucci +6 more
TL;DR: New embedding techniques for visualizing semantic and syntactic analogies, and the corresponding tests to determine whether the resulting views capture salient structures are introduced, to address a number of domain-specific tasks difficult to solve with existing tools.
Proceedings ArticleDOI
Lung nodule detection using 3D convolutional neural networks trained on weakly labeled data
TL;DR: This paper proposes to employ 3D convolutional neural networks to learn highly discriminative features for nodule detection in lieu of hand-engineered ones such as geometric shape or texture, and shows that the network trained using these weak labels can produce reasonably low false positive rates with a high sensitivity, even in the absence of accurate 3D labels.
Journal ArticleDOI
Multiple Kernel Sparse Representations for Supervised and Unsupervised Learning
TL;DR: This paper proposes to perform sparse coding and dictionary learning in the multiple kernel space, where the weights of the ensemble kernel are tuned based on graph-embedding principles such that class discrimination is maximized.