11–20 of 20 posts
This sounds to me like learning was just crawling to local optimum not actually exploring or making any breakthrough in understanding of the domain.
Just a note: Logistic regression on raw pixels already gets you 88% accuracy. Nearest-neighbors on raw pixels gets you 95% accuracy. You should not draw too much conclusion from a network with accuracy < 97%, because you probably just have bad hyperparameters (except for conclusions about which hyperparameters you need to tune).
Just a note: Logistic regression on raw pixels already gets you 88% accuracy. Nearest-neighbors on raw pixels gets you 95% accuracy. You should not draw too much conclusion from a network with accuracy < 97%, because you probably just have bad hyperparameters (except for conclusions about which hyperparameters you need to tune).
do you have a source for these? ta
Earlier quoted context omitted.
If possible, send it off to a web worker? That free's up the UI thread Edit: So it's the rendering that's hard on the CPU. Canvas would probably improve performance. Also, the graphic is so simple and there doesn't seem to be any event listeners on the edges themselves, that converting should be trivial :)
Hmm, that sounds like a promising idea...
Too slow; didn't wait to load. Has anyone tried training a neural network on anything that isn't the NIST digits? I've seen that one so done to death and a dearth of other examples that I'm starting to get skeptical that it would work on any other cases. Or is it that the data is expensive and the data "scientist" is cheap?
Too slow; didn't wait to load. Has anyone tried training a neural network on anything that isn't the NIST digits? I've seen that one so done to death and a dearth of other examples that I'm starting to get skeptical that it would work on any other cases. Or is it that the data is expensive and the data "scientist" is cheap?
I basically only see to-do list apps for new frameworks. So therefore frameworks can only make to-do lists.
Can anyone explain how the "floats" that are the output of the last layer correspond to the individual digits?
Can anyone explain how the "floats" that are the output of the last layer correspond to the individual digits?
The largest float in the output layer (while the graph is yellow) is the activation. The largest activation in the final layer is the network's "guess". The guess is the index of the last layer, which corresponds to a particular digit.
So I guess during training you're telling it that correct answers should be 1 and the incorrect answers should be 0.
Do the encoding choices that you make regarding the input / output of a neural network influence its performance at all? Maybe for MNIST the way you have it is the most common approach?
Earlier quoted context omitted.
The largest float in the output layer (while the graph is yellow) is the activation. The largest activation in the final layer is the network's "guess". The guess is the index of the last layer, which corresponds to a particular digit.
Awesome, I just flipped that switch at the top and can see how it calculates the individual handwritten inputs. Great demo! So I guess during training you're telling it that correct answers should be 1 and the incorrect answers should be 0. Do the encoding choices that you make regarding the input / output of a neural network influence its performance at all? Maybe for MNIST the way you have it is the most common app…