Sublime

general powers of reasoning and abstraction. Artificial neural networks neglect an essential point: human learning is not just the setting of a pattern-recognition filter, but the forming of an abstract model of the world.

DL involves layers upon layers of learning (neural networks), enabling the robot to understand complex patterns and make decisions similar to a seasoned barista.

And, finally, deep learning is about static translations, from an input to a label (a picture of a cat to the label cat), but reading is a dynamic process. When you use statistics to translate a story that begins Je mange une pomme to I eat an apple, you don’t need to know what either sentence means, if you can recognize that in previous bitexts je