microsoft
Neural Network isn't how children learns
"We can construct a so-called artificial neural network inside a computer, and then try to teach it to solve problems by giving it examples. This process is similar to how a newborn child learns about his or her surroundings by making observations."
Uh, no. Neural networks are inspired by how neurons in our brain works internally, with A LOT of connections between different neurons, the same as layers in a neural network. But it's not how children learns. How this works with neural networks is that you give it A LOT OF DATA with specified connections and it builds an internal representation getting closer and closer to the result you expect. Also known as a model.
Children doesn't learn like that. A child learns more with smaller steps (it's called "baby steps" for a reason), by filtering out a lot of noise and focusing on single things and build up understanding of the world that way. Just like any other human learns things really. You don't learn a language by spamming data, you learn it step by step. Good luck feeding whole internet to a child and see how that goes regarding learning about things.
