Abstract: Disclosed is a method for enhancing memory utilization and throughput of a computing platform in training a deep neural network (DNN). The critical features of the method includes: calculating a memory size for every operation in a computational graph, storing the operations in the computational graph in multiple groups with the operations in each group being executable in parallel and a total memory size less than a memory threshold of a computational device, sequentially selecting a group and updating a prefetched group buffer, and simultaneously executing the group and prefetching data for a group in the prefetched group buffer to the corresponding computational device when the prefetched group buffer is update. Because of group execution and data prefetch, the memory utilization is optimized and the throughput is significantly increased to eliminate issues of out-of-memory and thrashing.

Abstract: Disclosed is a method for enhancing memory utilization and throughput of a computing platform in training a deep neural network (DNN). The critical features of the method includes: calculating a memory size for every operation in a computational graph, storing the operations in the computational graph in multiple groups with the operations in each group being executable in parallel and a total memory size less than a memory threshold of a computational device, sequentially selecting a group and updating a prefetched group buffer, and simultaneously executing the group and prefetching data for a group in the prefetched group buffer to the corresponding computational device when the prefetched group buffer is update. Because of group execution and data prefetch, the memory utilization is optimized and the throughput is significantly increased to eliminate issues of out-of-memory and thrashing.

Abstract: Disclosed herein are composite polypeptide. According to various embodiments, the composite polypeptide includes a parent polypeptide and a metal binding motif capable of forming a complex with a metal cation. The composite polypeptide may be conjugated with a linker unit having a plurality of functional elements to form a multi-functional molecular construct. Alternatively, multiple composite polypeptides may be conjugated to a linker unit to form a molecular construct, or a polypeptide bundle. Linker units suitable for conjugating with the composite polypeptide having the metal binding motif are also disclosed.

Abstract: A method for analyzing an image of a biopsy specimen to determine a probability that the image includes an abnormal region is provided. The method involves a two-stage image analysis and adopts a combination of deep convolutional neural networks and staged and/or parallel computing to perform image recognition and classification. Such two-stage nasopharyngeal carcinoma detection module can detect and predict whole slide images into probabilities related to the nasopharyngeal carcinoma.