Category: Deep Learning

Artificial intelligence, neural networks and deep learning are the terms redefining medical proficiency and patient care in the healthcare industry Deep neural networks consist of multiple layers that allow for machines to sieve through vast quantities of data, solving complex problems and unlocking answers. It

AI has become increasingly critical for radiologists in the 21st century. Aidoc CEO Elad Walach describes in Forbes magazine how radiologists can utilize AI to bolster three keys areas in medical care: Safeguarding health data – AI harnesses data to provide a fuller picture of a patient’s

Visual attention mechanisms are known to be important components of modern computer vision systems and are an inherent part of state-of-the-art achievements in almost all fields: object detection, image-captioning, and more. Most conventional visual attention mechanisms use medical image captioning and VQA (visual question answering)

Neural networks are now practically doing most of the coding instead of us (and better than us) in many fields, but we don’t have a satisfactory methodology for testing their behavior. A very interesting recent paper that was covered on “The Morning Paper” blog, shows

A relatively recent paper by Baidu (Dec 2017) that was covered in The Morning Paper has empirically demonstrated something fascinating that could have major implications on the management of deep learning projects— Deep Learning output errors decrease predictably as a “power-law” of the training set size:  (m is the number