
Wrapped Loss Function for Regularizing Nonconforming Residual Distributions
Multioutput is essential in machine learning that it might suffer from ...
read it

Emergent Structures and Lifetime Structure Evolution in Artificial Neural Networks
Motivated by the flexibility of biological neural networks whose connect...
read it

Towards Robust Direct Perception Networks for Automated Driving
We consider the problem of engineering robust direct perception neural n...
read it

Adma: A Flexible Loss Function for Neural Networks
Highly increased interest in Artificial Neural Networks (ANNs) have resu...
read it

Toward a Characterization of Loss Functions for Distribution Learning
In this work we study loss functions for learning and evaluating probabi...
read it

Only sparsity based loss function for learning representations
We study the emergence of sparse representations in neural networks. We ...
read it

Integration of Clinical Criteria into the Training of Deep Models: Application to Glucose Prediction for Diabetic People
Standard objective functions used during the training of neuralnetwork...
read it
Empirical Strategy for Stretching Probability Distribution in Neuralnetworkbased Regression
In regression analysis under artificial neural networks, the prediction performance depends on determining the appropriate weights between layers. As randomly initialized weights are updated during backpropagation using the gradient descent procedure under a given loss function, the loss function structure can affect the performance significantly. In this study, we considered the distribution error, i.e., the inconsistency of two distributions (those of the predicted values and label), as the prediction error, and proposed weighted empirical stretching (WES) as a novel loss function to increase the overlap area of the two distributions. The function depends on the distribution of a given label, thus, it is applicable to any distribution shape. Moreover, it contains a scaling hyperparameter such that the appropriate parameter value maximizes the common section of the two distributions. To test the function capability, we generated ideal distributed curves (unimodal, skewed unimodal, bimodal, and skewed bimodal) as the labels, and used the Fourierextracted input data from the curves under a feedforward neural network. In general, WES outperformed loss functions in wide use, and the performance was robust to the various noise levels. The improved results in RMSE for the extreme domain (i.e., both tail regions of the distribution) are expected to be utilized for prediction of abnormal events in nonlinear complex systems such as natural disaster and financial crisis.
READ FULL TEXT
Comments
There are no comments yet.