Expert level GO and chess are here, while selfdriving cars and humanlevel computer vision and speech recognition are rapidly becoming realities. Meanwhile, despite hype about "precision medicine" and "big medical data", the daytoday practice of neurology continues to rely almost entirely on human expertise. In this talk I will introduce a range of realworld clinical problems for which computing, data science, machine learning, engineering, and other technical approaches can improve neurology, and why previous attempts at solving some of these problems have failed. These problems include: predicting which patients with brain injuries will have seizures; detecting seizures and seizurelike patterns in streaming brain monitoring (electroencephalography, EEG) data streams; diagnosing epilepsy in patients who have it, and avoiding misdiagnosing it in patients who don't; predicting which epilepsy patients will benefit from existing therapies; predicting whether a comatose patient will eventually recover consciousness; detecting impending cerebral infarction (stroke) in patients with brain aneurysms; automating the delivery of anesthesia to patients with acute brain swelling or lifethreatening seizures; computing a patient's level of consciousness from the EEG and EKG signals; diagnosing delirium; and tracking sleep stages. For each of these problems, we will point out