I am following up on a paper that demonstrates using deep learning (CNN) for classification. Specifically, their approach transformed the spatial data into fixed-length segments appropriate for CNN requirements. In their work, the
channel's dimension consists of 3-kinematics of
min_speed, avg_speed, max_speed.
Based on the outcome of their work, the model achieves 80+ on the accuracy, and well on other metrics. Out of curiosity, I took the task to replicate their work and was successful.
However, on a further check, I decided to take a look at the distribution of these kinematics computed per class before feeding to the CNN, in a boxplot. It turns out that a lot of data points fall as outliers.
So I begin to doubt.
- Are we feeding the network with instances full of outliers despite this interesting result?
- How does feeding a deep learning algorithm with data points full of outliers affect it´s performance?
- Should we expect the network to learn representation from what seems to be outliers in the first place?