I have a series as y (40 values from sales) and need to use neural networks in a matlab symlink to forecast the future values of y as in times(41,42,43,......50)
An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurones) working in unison to solve specific problems. ANNs, like people, learn by example. An ANN is configured for a specific application, such as pattern recognition or data classification, through a learning process.
There are many methods for time series forecasting some of them are old and some of them are novel .
Time series prediction divide in to two major categories the first one is qualitative and the second one is quantitative .
Time series forecasting with Neural Networks belong to the second category.
To forecast future values of time series you have many choices but LSTM and GRU neural networks are more powerful to this end . you can also employ BiLSTM or hybrid methods like CNN-LSTM and so on . recently I have read an article which has utilized XGboost in python to forecast time series .
By the way provide a simple search on Youtube, google, Github and other sources to find valuable information about this topic also you can benefit from scripts and codes which provided by other researchers and published for free use .