Deep reinforcement learning (DRL) brings the power of deep neural networks to bear on the generic task of trial-and-error learning, and its effectiveness has been convincingly demonstrated on tasks such as Atari video games and the game of Go. However, contemporary DRL systems inherit a number of shortcomings from the current generation of deep learning techniques. For example, they require ver...

OBJECTIVE To propose Irish CT diagnostic reference levels (DRLs) by collecting radiation doses for the most commonly performed CT examinations. METHODS A pilot study investigated the most frequent CT examinations. 40 CT sites were then asked to complete a survey booklet to allow the recording of CT parameters for each of 9 CT examinations during a 12-week period. Dose data [CT volume index (C...

In 2015, Google’s Deepmind announced an advancement in creating an autonomous agent based on deep reinforcement learning (DRL) that could beat a professional player in a series of 49 Atari games. However, the current manifestation of DRL is still immature, and has significant drawbacks. One of DRL’s imperfections is its lack of “exploration” during the training process, especially when working ...

Today’s large-scale services generally exploit looselycoupled architectures that restrict functionality requiring tight cooperation (e.g., leader election, synchronization, and reconfiguration) to a small subset of nodes. In contrast, this work presents a way to scalably deploy tightlycoupled distributed systems that require significant coordination among a large number of nodes in the wide are...

Neural function is dependent upon the proper formation and development of synapses. We show here that Wnt5 regulates the growth of the Drosophila neuromuscular junction (NMJ) by signaling through the Derailed receptor. Mutations in both wnt5 and drl result in a significant reduction in the number of synaptic boutons. Cell-type specific rescue experiments show that wnt5 functions in the presynap...

In this paper, we introduce a new set of reinforcement learning (RL) tasks in Minecraft (a flexible 3D world). We then use these tasks to systematically compare and contrast existing deep reinforcement learning (DRL) architectures with our new memory-based DRL architectures. These tasks are designed to emphasize, in a controllable manner, issues that pose challenges for RL methods including par...

Deep Reinforcement Learning (DRL) has had several breakthroughs, from helicopter controlling and Atari games to the Alpha-Go success. Despite their success, DRL still lacks several important features of human intelligence, such as transfer learning, planning and interpretability. We compare two DRL approaches at learning and generalization: Deep Q-Networks and Deep Symbolic Reinforcement Learni...

Background  It is remain a main concern that pediatric chest radiographies contribute to the significant radiation exposure to the thyroid gland as a more susceptible organ to radiation induced cancer. The aim of this study was to evaluate the entrance surface dose (ESD) of pediatric chest radiography compared to the diagnostic reference levels (DRL) and evaluation the efficacy of the lead (Pb)...

In the noisy intermediate-scale quantum era, optimal digitized pulses are requisite for efficient control. This goal is translated into dynamic programming, in which a deep reinforcement learning (DRL) agent gifted. As reference, shortcuts to adiabaticity (STA) provide analytical approaches adiabatic speedup by pulse Here, we select single-component control of qubits, resembling ubiquitous two-...