We used deep convolutional networks on spectrograms for a spoken language identification task. We had around 95% accuracy on a dataset provided in this TopCoder contest. The details are here. Plain convolutional networks do not capture the temporal characteristics, so for example in this work the output of the convolutional network was fed to a … Read more
Supervised learning: You get a bunch of photos with information about what is on them and then you train a model to recognize new photos. You have a bunch of molecules and information about which are drugs and you train a model to answer whether a new molecule is also a drug. Unsupervised learning: You … Read more
For the multi-class case, everything you need can be found from the confusion matrix. For example, if your confusion matrix looks like this: Then what you’re looking for, per class, can be found like this: Using pandas/numpy, you can do this for all classes at once like so: FP = confusion_matrix.sum(axis=0) – np.diag(confusion_matrix) FN = … Read more
Since you ask this very basic question, it looks like it’s worth specifying what Machine Learning itself is. Machine Learning is a class of algorithms which is data-driven, i.e. unlike “normal” algorithms it is the data that “tells” what the “good answer” is. Example: a hypothetical non-machine learning algorithm for face detection in images would … Read more