Cognitive deficits associated with Huntington disease (HD) are generally dominated by executive function disorders often associated with disinhibition and impulsivity/compulsivity. Few studies have directly examined symptoms and consequences of behavioral disinhibition in HD and its relation with decision-making. To assess the different forms of impulsivity in a transgenic model of HD (tgHD rat...

30 Wake Forest School of Medicine This study examined the effects of venlafaxine and quetiapine in a nonhuman primate model predictive of antidepressant drug effects. Twelve experimentally naïve male cynomolgus monkeys were trained to respond under a food-reinforcement schedule shown to have predictive validity in models of antidepressant activity (a differentialreinforcement-of-low rates; DRL ...

We study the problem of generating interpretable and verifiable policies through reinforcement learning. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, in which the policy is represented by a neural network, the aim in Programmatically Interpretable Reinforcement Learning (PIRL) is to find a policy that can be represented in a high-level programming language. Such programmatic p...

BACKGROUND Medical X-rays are the largest man-made source of public exposure to ionizing radiation. While the benefits of Computed Tomography (CT) are well known in accurate diagnosis, those benefits are not risk-free. CT is a device with higher patient dose in comparison with other conventional radiation procedures. OBJECTIVE This study is aimed at evaluating radiation dose to patients from ...

Reinforcement learning (RL) [1] differs from traditional supervised machine learning in the sense that it not only considers short-term consequences of actions/decisions, but also long-term outcomes. Because of recent advances in deep learning, model-free deep reinforcement learning (DRL) has proven successful in various applications, as with the success of a deep Q-network (DQN) in the Atari g...

Deep Reinforcement Learning (DRL) methods have performed well in an increasing numbering of high-dimensional visual decision making domains. Among all such visual decision making problems, those with discrete action spaces often tend to have underlying compositional structure in the said action space. Such action spaces often contain actions such as go left, go up as well as go diagonally up an...

OBJECTIVE Aiming at contributing to the knowledge on doses in computed tomography (CT), this study has the objective of determining dosimetric quantities associated with pediatric abdominal CT scans, comparing the data with diagnostic reference levels (DRL). MATERIALS AND METHODS The study was developed with a Toshiba Asteion single-slice CT scanner and a GE BrightSpeed multi-slice CT unit in...

Traditional multicast routing methods have some problems in constructing a tree. These include limited access to network state information, poor adaptability dynamic and complex changes the network, inflexible data forwarding. To address these defects, optimal problem software-defined networking (SDN) is tailored as multiobjective optimization problem, DRL-M4MR, an intelligent algorithm based o...