New ‘Artificial Intelligence Software’ Capable of ‘Near Human-Level’ Image-Recognition

Scientists with Stanford University and Google have developed two new artificially intelligent software programs capable of describing images with near human-level accuracy.

Stanford’s research paper, entitled “Deep Visual-Semantic Alignments for Generating Image Descriptions,” explains how specific details found in photographs and videos can be translated into written text.

“We present a model that generates free-form natural language descriptions of image regions,” the paper’s abstract states. “Our model leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between text and visual data.” .... http://www.prisonplanet.com