special feature How to Implement AI and Machine Learning The next wave of IT innovation will be powered by artificial intelligence and machine learning. We look at the ways companies can take advantage of it and how to get started. Read More One of the continuing problems with Deep Neural Networks (DNNs) is that humans typically do not understand how they achieve their amazing results. DNN models are trained on massive amounts of data until they surpass human accuracy, but the details of the models themselves are hidden inside thousands of equations. So, not human readable.How do neural networks see depth in single images? worth a read. We treat the neural network as a black box, only measuring the responses (in this case depth maps) to certain inputs. . . . [W]e modify or disturb the images, for instance by adding conflicting visual cues, and look for a correlation in the resulting depth maps. In other words, they mess with images to see how the model changes the depth map. This enables them to estimate which features the model relies on to estimate depth. Vertical position relative to the horizon. Depth order: which objects block others. Texture detail: closer objects have clearer textures. Apparent size. Shading and illumination. Human visual acuity is generally much better than even the highest resolution photographs, so not all of these features are accessible to DNNs. For example, photos, especially compressed ones, will tend to smear fine textures. Results In their experiments, the researchers found… [Read full story]
ZDNet is a business technology news website published by CBS Interactive, along with TechRepublic. The brand was founded on April 1, 1991, as a general interest technology portal from Ziff Davis and evolved into an enterprise IT-focused online publication owned by CNET Networks.