"WTF? Why can't I get the accuracy of this classifier higher?!" (manually looks at training set targets) "Oh. I see"
Oh yea. Had a small dataset recently. Though, "way too tiny for deep methods. Stick to basics." Then, I tried it anyway. 20% improvement.
-
-
"20% improvement" in minority class?
-
Yes. I think it was just a lucky example, but it took 20 minutes of testing, so it was affordable luck.
- 2 more replies
New conversation -
-
-
Very good.!What package(s) in R/Py would you recommend for CNNs?
-
Keras is awesome for prototyping. https://keras.io/ Here's a nice tutorial for doing CNN in Keras for MNIST: https://github.com/ml4a/ml4a-guides/blob/master/notebooks/convolutional_neural_networks.ipynb …
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
