Questions tagged [classifier]
The classifier tag has no summary.
76 questions
-1votes
0answers
25views
Tips for increasing classification performance
I'm training a Multi View CNN on a ModelNet10 dataset (5000 3d meshes of 10 classes) to later use it as an encoder part for AutoEncoder model for 3d reconstruction. Each element of dataset is 40 ...
- 1
4votes
1answer
240views
How should I calculate AUROC if my (TPR,FPR) doesn't go till (1,1)? Should it be area just under the curve or should I include 1 and calculate?
I am running a model where it generates song detections with a confidence value. I then validate it across an annotated dataset. I then plot the values of TPR and FPR at each confidence threshold, ...
0votes
1answer
60views
When Should a Classifier Be Preferred Over a Ranker in Recommendation or Search Ranking Systems?
I'm preparing for an ML system design interview and have a question about the choice of models in recommendation systems and similar domains like search ranking. When presenting several items to a ...
1vote
1answer
78views
How to tune the classification threshold in a cost-sensitive manner?
I have trained a classifier outputting probabilities for each class. I want to tune the decision threshold in such a way that it accounts for different costs/gains assigned to false positives ($FP$), $...
- 1,979
1vote
1answer
49views
What to do if I have a very low metric on one of the classes during multiclass classification?
I trained multiclass text classififer with fasttext. I have a very low metric on one of the classes. Here are results of metrics for each class on test data: ...
0votes
0answers
34views
how to get feature importance on unseen test data
I trained a random forest classifier with a set of features and saved the model. (the features were selected based on their correlations with the response variable. Only those features with ...
1vote
1answer
92views
What do the terms in this equation $$θ_{1}x_{1}+θ_{2}x_{2}+θ_{0}=0$$ represent?
I am currently learning ML from a course by MIT. I am from a non tech background and unable to understand some equations shown in this lecture of Linear Classifiers: https://youtu.be/yOKDzd73KgM?t=57 ...
- 11
1vote
2answers
61views
Using a Genetic Algorithm in junction with a digit classifier CNN to create an "MNIST image generator"
I'm trying to use a genetic algorithm that optimizes a 28x28 matrix (its shape) to make it look like an image of the number 7 that could be found in the MNIST image dataset. My attempt is to basically ...
0votes
1answer
84views
Ensemble method with Blackbox Classifiers
I have few pre-trained blackbox models that are used for classification tasks. I want to know what is the best way to combine these models into a single classifier that does not require any re-...
0votes
2answers
318views
Is there no reason to ever use naive bayesian learning?
I found this slide in the university course on machine learning I am currently taking. The reasons seem sound but I have not found this confirmed anywhere everywhere I read that for certain types of ...
1vote
1answer
44views
ANN time series classification validation loss never decreases
Problem statement: E2E classifier Input: [7x3600] time series of physiological parameters recorded from a medical device. Output: I am trying to learn a binary classifier to determine if the device is ...
- 11
0votes
0answers
29views
What does "n∼1/d" mean?
Or rather, what is the "~" notation mean? For reference, I'm trying to understand this section from a sci-kit learn documentation page.
- 101
1vote
2answers
96views
How does a classifier work on categorical features?
I have a dataset with a categorical variable year which has the years:: 2015,2016,2017,2018,2019. What I am trying to understand is how does a classifier work on this feature? Let's take a decision ...
2votes
1answer
122views
Using Latitude/Longitude and site ID in classification of daily air pollution levels
Assume that there is a very large dataset of hundreds of sites which contains only the PM2.5 level, the site ID, and the Latitude and Longitude as features. The independent feature to be predicted is ...
- 121
0votes
1answer
22views
output F1-score instead of Accuracy
I have the code below outputting the accuracy. How can I output the F1-score instead? ...
