Why you can't afford to ignore deep learning
summary
Argues deep learning already outperforms humans on vision and speech tasks, cites a state-of-the-art algorithm for early detection of lung cancer built with standard deep nets and developed in months with surprisingly strong results, emphasizes 10x improvement in survival odds when cancer is detected early, describes speech systems trained end-to-end on waveforms, lists Theano/TensorFlow/MXNet and GPU/custom hardware, and frames human+machine augmentation as the route to clinical adoption.
AI-written summary · about
related talks
25mDeep Learning in Biomedicine: Challenges and Opportunities
45mIntroduction To Deep Learning
03mInterview
40mMachines are Learning
29mCancer diagnostics enabled by machines: finding and classifying single tumor....
37mRecent Solutions Using Deep Learning Models/ The How and Why
01h 00mDeep Learning Revolution: Rethinking Machine Learning Pipelines
58mHealthcare with AI of the Future