Search Results - "Ebrahimi, Abdolghani"

Optimal control of a queue under a quality-of-service constraint with bounded and unbounded rates by Ebrahimi, Abdolghani, Ghosh, Arka P.

“…We consider a simple Markovian queue with Poisson arrivals and exponential service times for jobs. The controller chooses state-dependent service rates from an…”
Get full text

Topics in Deep Learning and Deep Reinforcement Learning by Ebrahimi, Abdolghani

“…Deep Learning (DL) and Deep Reinforcement Learning(DRL) are two areas within machine learning which use neural networks to approximate functions. They have…”
Get full text

Nested Multi-view Image Classification by Ebrahimi, Abdolghani, Stec, Alexander, Klabjan, Diego, Utke, Jean

“…There are classification tasks that take as inputs groups of images rather than single images. In order to address such situations, we introduce a nested…”
Get full text

Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation by Ebrahimi, Abdolghani, Klabjan, Diego

“…Existing methods of pruning deep neural networks focus on removing unnecessary parameters of the trained net-work and fine tuning the model afterwards to find…”
Get full text

Rate control of a queue with quality-of-service constraint under bounded and unbounded action spaces by Ebrahimi, Abdolghani

“…We consider a simple Markovian queue with Poisson arrivals and exponential service times for jobs. The controller can choose service rates from a specified…”
Get full text

Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation by Ebrahimi, Abdolghani, Klabjan, Diego

“…Existing methods of pruning deep neural networks focus on removing unnecessary parameters of the trained network and fine tuning the model afterwards to find a…”
Get full text

Generative Adversarial Nets for Multiple Text Corpora by Ebrahimi, Abdolghani, Klabjan, Diego, Wang, Baiyang

“…Generative adversarial nets (GANs) have been successfully applied to the artificial generation of image data. In terms of text data, much has been done on the…”
Get full text

Layer Flexible Adaptive Computation Time by Zhang, Lida, Ebrahimi, Abdolghani, Klabjan, Diego

“…Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the…”
Get full text

Layer Flexible Adaptive Computational Time by Zhang, Lida, Ebrahimi, Abdolghani, Klabjan, Diego

“…Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the…”
Get full text

Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories by Harmon, Mark, Ebrahimi, Abdolghani, Lucey, Patrick, Klabjan, Diego

“…In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories. Previous approaches to similar problems center…”
Get full text