Timeline for Is data science mathematically interesting?
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 4, 2019 at 6:38 | comment | added | littleO | True, it's a very insightful / enlightening answer, I was just being overly nitpicky! | |
| Oct 4, 2019 at 6:33 | comment | added | Paul Siegel | @littleO Fair enough, I guess. For the purposes of this discussion "optimization algorithm" means an algorithm which takes as input a function defined on a finite set of points in some space and produces as output a probability distribution which "best approximates" the input function in an appropriate sense. It was not intended to refer to the actual numerical analysis used to construct the probability distribution. I tried to suppress these details deliberately because the same remarks apply to a broader class of data science problems than just classification. | |
| Oct 4, 2019 at 5:58 | comment | added | littleO | I know that one trains a neural network (for example) by using an optimization algorithm such as stochastic gradient descent; I was just making the point that there's a distinction between a classifier and the optimization algorithm which is used to train the classifier. | |
| Oct 4, 2019 at 5:34 | comment | added | Paul Siegel | @littleO Sure it is! Rather, training a classification algorithm is. Deep neural networks, including CNN's, have a large number of parameters which specify how data moves between the neurons, and the process of training a neural network corresponds to finding - usually via some form of gradient descent - a collection of parameters which minimizes an objective function. In the case of classification problems the objective function is chosen to punish classification errors in training data - cross entropy is a typical choice. Most other classification algorithms can be viewed similarly. | |
| Oct 4, 2019 at 3:51 | comment | added | littleO | Very interesting answer, but the first paragraph seems to blur the distinction between an optimization algorithm and a classification algorithm. A convolutional neural network is not an optimization algorithm, for example. | |
| Oct 3, 2019 at 23:11 | comment | added | Juan Sebastian Lozano | This is such an interesting framing! | |
| Oct 3, 2019 at 23:02 | history | edited | Paul Siegel | CC BY-SA 4.0 |
added 1 character in body
|
| S Oct 3, 2019 at 22:57 | history | answered | Paul Siegel | CC BY-SA 4.0 | |
| S Oct 3, 2019 at 22:57 | history | made wiki | Post Made Community Wiki by Paul Siegel |