This document provides a comparative evaluation of the performance of a deep learning network for different combinations of parameters and hyper-parameters. Although there are numerous studies that report on performance in deep learning networks for ordinary data sets, their performance on small data sets is much less evaluated. The objective of this work is to demonstrate that such a challenging small data set, such as a welding X-ray image data set, can be trained and evaluated obtaining high precision and that it is possible thanks to data augmentation. In fact, this article shows that data augmentation, also a typical technique in any learning process on a large data set, plus that two image channels, such as channels B (blue) and G (green), both are replaced by the Canny edge map and a binary image provided by an adaptive Gaussian threshold, respectively, gives to the network a 3% increase in accuracy, approximately. In summary, the objective of this work is to present the methodology used and the results obtained to estimate the classification accuracy of three main classes of welding defects obtained on a small set of welding X-ray image data.
Visual neuroprosthesis, that provide electrical stimulation along several sites of the human visual system, constitute a potential tool for vision restoration for the blind. Scientific and technological progress in the fields of neural engineering and artificial vision comes with new theories and tools that, along with the dawn of modern artificial intelligence, constitute a promising framework for the further development of neurotechnology. In the framework of the development of a Cortical Visual Neuroprosthesis for the blind (CORTIVIS), we are now facing the challenge of developing not only computationally powerful tools and flexible approaches that will allow us to provide some degree of functional vision to individuals who are profoundly blind. In this work, we propose a general neuroprosthesis framework composed of several task-oriented and visual encoding modules. We address the development and implementation of computational models of the firing rates of retinal ganglion cells and design a tool — Neurolight — that allows these models to be interfaced with intracortical microelectrodes in order to create electrical stimulation patterns that can evoke useful perceptions. In addition, the developed framework allows the deployment of a diverse array of state-of-the-art deep-learning techniques for task-oriented and general image pre-processing, such as semantic segmentation and object detection in our system’s pipeline. To the best of our knowledge, this constitutes the first deep-learning-based system designed to directly interface with the visual brain through an intracortical microelectrode array. We implement the complete pipeline, from obtaining a video stream to developing and deploying task-oriented deep-learning models and predictive models of retinal ganglion cells’ encoding of visual inputs under the control of a neurostimulation device able to send electrical train pulses to a microelectrode array implanted at the visual cortex.
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.