4
votes
Can classification model B trained on data labeled by classification model A exceed the performance of model A?
For strictly supervised methods, I would not expect model B to perform significantly better than model A. The only way model B can do better than model A is by correctly classifying samples for which ...
1
vote
How can I export the best classifier from my code to a model for real future usage?
The logic seems completely fine.
In your place, I would save all the model's performances inside a dictionary to keep track and use any of them in case I need them.
...
1
vote
High Performance Classification or Similarity Algorithim for Mixed Data Types?
You have many option, one would be to train a classification model where you encode categorical features with one-hot encoding and let the algorithm do the rest.
With similarity measures I would ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
classification × 2997machine-learning × 1262
python × 386
neural-network × 310
deep-learning × 295
scikit-learn × 234
class-imbalance × 202
nlp × 162
regression × 148
keras × 143
time-series × 138
multiclass-classification × 138
data-mining × 137
svm × 134
predictive-modeling × 125
decision-trees × 116
random-forest × 114
clustering × 107
logistic-regression × 107
dataset × 99
feature-selection × 97
multilabel-classification × 90
machine-learning-model × 84
supervised-learning × 80
image-classification × 78