Relevant diagnostic information may be lost when images are reduced in size. Therefore, for optimal presentation, the smaller images should be enlarged rather than the larger ones reduced.
Large-scale particle physics experiments face challenging demands for highthroughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. As an example, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC. Using Microsoft Azure Machine Learning deploying Intel FPGAs to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework deployed as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600-700 inferences per second using an image batch of 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada. one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.
OBJECTIVES
To compare the standards of periapical radiography with a CCD-image receptor with film.
METHODS
Three radiography technicians exposed a total of fifty teeth from all areas of the jaws using either size 1 or size 2 film and the Sidexis (Siemens, Bensheim, Germany) direct digital dental radiography system with the appropriate film holders. Image quality was assessed by two dental radiologists for nine individual criteria and overall, on a three-point scale.
RESULTS
There was a significant difference between film and sensor exposures (P < 0.014). Six per cent of dental films required retakes compared with 28% with the sensor.
CONCLUSION
Periapical radiography with a CCD sensor leads to more errors and thus more retakes than conventional film.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.