Why are neural networks predictive?
This depends on the problem to be dealt with. How many years of data are the samples for training the network based on, and how many years of data are the corresponding predictions.
For example, in power load forecasting, when short-term load forecasting is performed, the input samples are the load data of the last few days, so the forecast is naturally the last few days, and it cannot be longer.
For long-term load forecasting, the training samples are load data in units of years, and the load for several years or even decades can be predicted. For another example, population growth forecasts are generally based on multi-year forecasts.
Google AI Writing Project: Neural Network Pseudo-Original
Help: Use a neural network to make a data prediction
The following code is the code for the BP neural network to predict the sales volume of 37-56 weeks: % x is the original sequence load sales volume.matdata=Cx=data';t=1:length(x);lag=2;fn=length( t);[f_out,iinput]=BP(x,lag,fn);%Forecast year or a certain time period t1=fn:fn+20;n=length(t1);t1=length(x)+1: length(x)+n;%The number of prediction steps is fnfn=length(t1); [f_out,iinput]=BP(x,lag,fn);P=vpa(f_out,5);[t1' P']% Draw the forecast figure figure(6), plot(t,x,'b*-'),hold onplot(t(end):t1(end),[iinput(end),f_out],'rp-'), grid onxlabel('weeks'), ylabel('sales');str=['BP neural network forecast',num2str(length(x)+1),'-',num2str(length(x)+20) ,'weekly sales'];title(str)str1=['1-',num2str(length(x)),'weekly sales'];str2=[num2str(length(x)+1), '-',num2str(length(x)+20),'weekly forecasted sales']; legend(str1,str2) run the result copywriting dog .
The BP neural network makes data predictions, and the predicted results feel wrong, please guide me
How to realize the regression prediction of continuous variables with neural network?
Neural network was originally a model of machine learning, but its training time is not advantageous compared with other models, and the results are not satisfactory, so it has not been widely used.
However, with the in-depth study of mathematics and the improvement of the quality of computer hardware, especially the emergence of GPU, it has provided a basis for the wide application of deep learning.
The GPU was originally designed to bring high-quality visual experience to gamers. Because of its excellent ability to handle matrix operations, it is also used for model training in deep learning. In the past, a model that could only be trained in dozens of days was trained several times on the GPU. It can be trained in one day, which greatly reduces the training time of deep learning, so the application of deep learning is increasing.
Neural network is the most important model of deep learning. Artificial neural network (ANN) is the most basic neural network structure, and its working principle is very similar to the nerves in the human brain.
A neuron is the working unit of ANN. Each neuron contains weights and biases. The neurons pass the values passed by the neurons of the previous layer through weight and bias calculations to obtain new results, and pass the results to the next layer. Layer neurons, through continuous transmission, finally obtain the output result.
In order to use the neural network to realize the regression prediction of continuous variables, the data of the N-dimensional variable needs to be used as input, and the hidden layer and the number of neurons in each layer are set in the middle. As for the number of hidden layers, multiple trainings are required. In order to get a more accurate number of layers.
However, there will be errors between the value of the final output layer and the value of the actual variable. The neural network will continuously train and change the values of weights and biases to make the error as small as possible. When the error is small to a certain extent, the regression of the neural network Even if the prediction is successful.
Python is usually used to build a neural network. Python comes with some libraries for deep learning. When performing regression prediction, we only need to call the function and set a few parameters, such as the number of hidden layers and the number of neurons, etc., and the rest The only thing is to wait for the model to train itself, and finally complete the regression prediction, which is very convenient.
Can Neural Networks Make Predictions on Data? Mathematical Modeling
The neural network itself is a mathematical approximation model. The network was originally derived from the function approximation technology in mathematics. According to statistical laws, it is combined into a linear superposition network, and some highly nonlinear models in reality are analyzed from it. The neural network itself is a Mathematical modeling is only easier to carry out engineering practice after sorting out. As for prediction, it is of course possible.