96 citations · 209 across the 20 of their papers we have counts for
6 papers · 1 filter
Pseudo-Inverted Bottleneck Convolution for DARTS Search Space
Arash Ahmadian, Louis S. P. Liu, Yue Fei +2
Differentiable Architecture Search (DARTS) has attracted considerable attention as a gradient-based neural architecture search method. Since the introduction of DARTS, there has be…
Exploiting Explainable Metrics for Augmented SGD
Mahdi S. Hosseini, Mathieu Tuli, Konstantinos N. Plataniotis
Explaining the generalization characteristics of deep learning is an emerging topic in advanced machine learning. There are several unanswered questions about how learning under st…
Towards Robust and Automatic Hyper-Parameter Tunning
Mathieu Tuli, Mahdi S. Hosseini, Konstantinos N. Plataniotis
The task of hyper-parameter optimization (HPO) is burdened with heavy computational costs due to the intractability of optimizing both a model's weights and its hyper-parameters si…
P4AI: Approaching AI Ethics through Principlism
Andre Fu, Elisa Ding, Mahdi S. Hosseini +1
The field of computer vision is rapidly evolving, particularly in the context of new methods of neural architecture design. These models contribute to (1) the Climate Crisis - incr…
In Search of Probeable Generalization Measures
Jonathan Jaegerman, Khalil Damouni, Mahdi S. Hosseini +1
Understanding the generalization behaviour of deep neural networks is a topic of recent interest that has driven the production of many studies, notably the development and evaluat…
AdaS: Adaptive Scheduling of Stochastic Gradients
Mahdi S. Hosseini, Konstantinos N. Plataniotis
The choice of step-size used in Stochastic Gradient Descent (SGD) optimization is empirically selected in most training procedures. Moreover, the use of scheduled learning techniqu…