Probability density computation neural network for time series data

Traditional point prediction systems compute a most probable value without representing the uncertainty. The point prediction is a value close to the mean or the median. A person or an autonomous system may require a prediction corresponds to a different cumulative probability (CP), known as the uncertainty bound. Therefore, in this paper, we present a probability density computing neural network (NN) training procedure. To overcome the limitation of an effective cost function, example uncertainty bounds are constructed with the help of correlation. Similar occurrences are selected through the correlation and weights are assigned to each similar occurrence based on both shape-similarities and ratio based similarities. Then example results from similar samples are considered. The normalized weighted distribution of examples is the probability distribution. Finally, a shallow NN with the example probability density is trained. The NN receives input circumstances and the cumulative probability. The NN returns the value corresponds to the given circumstances and the cumulative probability. Proposed cumulative probability computation point from a shallow NN is less computation extensive compared to the correlation-based similarity analysis. Moreover, we propose a probability density computation NN for the first time. We also upload an example code to the GitHub.