Broad research interests and related applications: My research is in the area of stochastic systems, computational methods for sensing, estimation, and control problems, with a focus on robotic systems. In real-world systems, uncertainty (both in the system model and sensory readings) is omnipresent. A few of the vast set of applications for this research include (i) Motion planning for mobile ...

| 2017 | 1 Seyed-Hossein Abtahi1,2, Mohammad-Ali Abtahi1,2, Seyed Ali Akbar Mortazavi1,2, Hamidreza Jahanbani-Ardakani2,3,4, Mehdi Mazloumi5 1Department of Ophthalmology, School of Medicine, Isfahan University of Medical Sciences, 2Isfahan Eye Research Center, Isfahan University of Medical Sciences, 3Medical School, Isfahan University of Medical Sciences, 4Isfahan Medical Students Research Cent...

Acute lung injury (ALI) associated with systemic inflammatory response syndrome (SIRS) is a systemic complication following subarachnoid hemorrhage (SAH), but the incidence and influence on prognosis are unclear. The incidences of SIRS and ALI were surveyed in a prospective multicenter study of 96 patients admitted for SAH between December 2004 and June 2007. Hunt and Hess grade and Glasgow Out...

RATIONALE We hypothesise that elafin levels in acute lung injury (ALI) decrease over time due, in part, to proteolytic degradation as observed in other lung diseases. OBJECTIVES The aim of this study was to characterise temporal changes in elafin concentration in patients with ALI and to evaluate whether a decrease in elafin levels is due to elevated protease activity. METHODS Bronchoalveol...

Machine learning algorithms for controlling devices will need to learn very quickly, with very few trials. Such a goal can be attained with concepts borrowed from continental philosophy and formalized using tools from the mathematical theory of categories. Illustrations of this approach are presented on a cyberphysical system: the slot car game, and also on Atari 2600 games.

In many real-world problems, reward signals received by agents are delayed or sparse, which makes it challenging to train a reinforcement learning (RL) agent. An intrinsic signal can help an agent explore such environments in the quest for novel states. this work, we propose general end-to-end diversity-augmented motivation deep encourages new states and automatically provides denser rewards. S...

We show how an ensemble ofQ-functions can be leveraged for more effective exploration in deep reinforcement learning. We build on well established algorithms from the bandit setting, and adapt them to the Q-learning setting. We propose an exploration strategy based on upper-confidence bounds (UCB). Our experiments show significant gains on the Atari benchmark.

This paper presents the selective use of eye-gaze information in learning human actions Atari games. Extensive evidence suggests that our eye movements convey a wealth about direction attention and mental states encode necessary to complete task. Based on this evidence, we hypothesize eye-gaze, as clue for direction, will enhance from demonstration. For purpose, propose augmentation (SEA) netwo...

This a rare case of adenoid hypertrophy in a 23 years old Saudi non-smoker female, who presented with severe bilateral nasal obstruction, mouth breathing, anterior nasal discharge, snoring for the last 7 months. The nasopharynx was examined by flexible nasopharyngoscope, which showed a big mass occupying the nasopharynx. Under general anesthesia, adenoidectomy was performed. Immediately after t...