Search⌘ K
Home
Courses
Understanding Deep Learning Applications in Rare Event Prediction

Refining Neural Networks with Class Weights

Explore how to refine neural networks for rare event prediction by applying class weights in loss functions. Understand the impact of penalizing misclassified minority samples, improving recall while managing false positives. Gain insight into balancing model performance with class weighting strategies in multi-layer perceptrons.

We'll cover the following...

Loss function

A rare event problem has very few positively labeled samples. Due to this, even if the classifier misclassifies the positive labels, their effect on the loss function is minuscule.

L(θ)=−1n∑i=1n(yilog(pi)+(1−yi)log(1−pi))\mathcal{L(\theta)}=−\frac{1}{n}\sum_{i=1}^{n}\big( y_{i}log(p_{i})+(1−y_{i})log(1−p_{i})\big)

where

  • yi∈0,1y_{i} ∈ 0,1 are the true labels.
  • pi=Pr[yi=1
...