Brett A. Story

TL;DR: A novel context‐aware deep convolutional semantic segmentation network is presented to effectively detect cracks in structural infrastructure under various conditions to segment the cracks on images with arbitrary sizes without retraining the prediction network.

TL;DR: In this paper, the authors conducted a replication experiment to determine whether handaxe morphology was influenced by raw materials of demonstrably different internal and external properties: flint, basalt, and obsidian.

TL;DR: In the CPNN, a competitive layer ranks kernels for each class and an optimum fraction of kernels are selected to estimate the class-conditional probability, which shows modest improvement in performance over the state of the art.

TL;DR: The authors found evidence that the fluted-point base acts as a "shock absorber" and increased point robustness and ability to withstand physical stress via stress redistribution and damage relocation, which would have provided a selective advantage to foragers on a largely unfamiliar landscape, who were ranging far from known stone sources and in need of longerlasting, reliable, and maintainable weaponry.

TL;DR: The computational framework of a Structural Impairment Detection System (SIDS) that processes the digital data streams of electronic sensors attached to critical components of a structure that comprises a competitive array of neural networks that can accurately describe the types and severity of likely impairments present in the structure.