133 citations · 310 across the 33 of their papers we have counts for
6 papers · 1 filter
Deep Adversarial Belief Networks
Yuming Huang, Ashkan Panahi, Hamid Krim +2
We present a novel adversarial framework for training deep belief networks (DBNs), which includes replacing the generator network in the methodology of generative adversarial netwo…
Community Detection and Improved Detectability in Multiplex Networks
Yuming Huang, Ashkan Panahi, Hamid Krim +1
We investigate the widely encountered problem of detecting communities in multiplex networks, such as social networks, with an unknown arbitrary heterogeneous structure. To improve…
Sparse Generative Adversarial Network
Shahin Mahdizadehaghdam, Ashkan Panahi, Hamid Krim
We propose a new approach to Generative Adversarial Networks (GANs) to achieve an improved performance with additional robustness to its so-called and well recognized mode collapse…
Joint Concept Matching based Learning for Zero-Shot Recognition
Wen Tang, Ashkan Panahi, Hamid Krim
Zero-shot learning (ZSL) which aims to recognize unseen object classes by only training on seen object classes, has increasingly been of great interest in Machine Learning, and has…
Analysis Dictionary Learning: An Efficient and Discriminative Solution
Wen Tang, Ashkan Panahi, Hamid Krim +1
Discriminative Dictionary Learning (DL) methods have been widely advocated for image classification problems. To further sharpen their discriminative capabilities, most state-of-th…
Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework
Arman Rahbar, Ashkan Panahi, Morteza Haghir Chehreghani +2
We develop a novel theoretical framework for understating OT schemes respecting a class structure. For this purpose, we propose a convex OT program with a sum-of-norms regularizati…