advanced loss function
Research Guide: Advanced Loss Functions for Machine Learning Models
Logistic loss functions don't perform very well during training when the data in question is very noisy. Such noise can be caused by outliers and mislabeled data. In this paper, Google Brain authors aim to solve the shortcomings of the logistic loss function by replacing the logarithm and exponential functions with their corresponding "tempered" versions. The authors introduce a temperature into the exponential function and replace the softmax output layer of neural nets with a high-temperature generalization. The algorithm used in the log loss is replaced by a low-temperature logarithm.
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.68)