The term "deep" comes from the idea that the algorithm is trying to learn something deeper than previous algorithms. In fact, the usual set of machine learning algorithms are termed shallow learning now.
The difference is that deep learning tries to model P(X) whereas shallow learning (SVM, NN, naive Bayes, etc..) try to learn P(X|Y) where X is your input space and Y is the label space.
In deep learning, these neural networks are not your usual NNs. Deep learning isn't just taking advantage of hardware scaling for more nodes and layers, rather it uses convolutional NNs which are slightly different.
Another difference is that deep learning is trying to learn an efficient representation for the inputs, i.e. automatic feature generation. This is not to say it trying to become an automatic unsupervised learning technique, but instead a supervised learning approach that takes care of the most time intensive and critical process (and typically unappreciated and overlooked) of any machine learning process -- feature extraction/generation.
I agree the guy in the article is an idiot, and will do our children a disservice by dumbing down the questions.
But if we're going to call him an idiot, unlucky, and dumber than a gorilla let's at least do a little math first... after all we're claiming to be math elitists here.
You realize this gorilla that gets 15/60 all the time is in your imagination. He exists as the ensemble average of an infinite population of gorillas.
The probability that a gorilla get 15 correct out of 60 isn't even 25% with four choices... it's closer to 11.8% Don't believe me? Go back to your probability 101 book and look up the binomial distribution (by the way this isn't directly specifically to the parent of my message, but the whole tree).
The probability of get 14/60 is 11.5%... so it's almost a wash. The probability of getting 10/60 is a little over 4%. You might say that is low, so let's keep going with the gorilla jokes, but it really isn't that surprising given you are looking at a single sample from the population. Getting 10 correct is also within two standard deviations from the mean, so again not surprising.
The guy in the article does sound like a jack***, and he will probably do more harm than good given his position. But for us to make smart-*** comments about the fact that he guessed and got 10 correction is worse.
Slashdot Mirror
The term "deep" comes from the idea that the algorithm is trying to learn something deeper than previous algorithms. In fact, the usual set of machine learning algorithms are termed shallow learning now. The difference is that deep learning tries to model P(X) whereas shallow learning (SVM, NN, naive Bayes, etc..) try to learn P(X|Y) where X is your input space and Y is the label space.
In deep learning, these neural networks are not your usual NNs. Deep learning isn't just taking advantage of hardware scaling for more nodes and layers, rather it uses convolutional NNs which are slightly different.
Another difference is that deep learning is trying to learn an efficient representation for the inputs, i.e. automatic feature generation. This is not to say it trying to become an automatic unsupervised learning technique, but instead a supervised learning approach that takes care of the most time intensive and critical process (and typically unappreciated and overlooked) of any machine learning process -- feature extraction/generation.
I agree the guy in the article is an idiot, and will do our children a disservice by dumbing down the questions. But if we're going to call him an idiot, unlucky, and dumber than a gorilla let's at least do a little math first ... after all we're claiming to be math elitists here.
You realize this gorilla that gets 15/60 all the time is in your imagination. He exists as the ensemble average of an infinite population of gorillas.
The probability that a gorilla get 15 correct out of 60 isn't even 25% with four choices... it's closer to 11.8% Don't believe me? Go back to your probability 101 book and look up the binomial distribution (by the way this isn't directly specifically to the parent of my message, but the whole tree).
The probability of get 14/60 is 11.5% ... so it's almost a wash. The probability of getting 10/60 is a little over 4%. You might say that is low, so let's keep going with the gorilla jokes, but it really isn't that surprising given you are looking at a single sample from the population. Getting 10 correct is also within two standard deviations from the mean, so again not surprising.
The guy in the article does sound like a jack***, and he will probably do more harm than good given his position. But for us to make smart-*** comments about the fact that he guessed and got 10 correction is worse.