Model Evaluation Test Harness - for developing and evaluating deep learning models for univariate time series forecasting. Source article: Jason Brownlee, Ph.D. Making Developers Awesome at Machine Learning http://machinelearningmastery.com/ Accessed on Oct 31, 2018
This source variant is using data from the US500 (S&P) Index, and this data will be updated periodically.
Multilayer Perceptron Model: The first network that we will evaluate is a multilayer Perceptron, or MLP for short.
Convolutional Neural Network Model: Convolutional Neural Networks, or CNNs, are a type of neural network developed for two-dimensional image data, although they can be used for one-dimensional data such as sequences of text and time series.
Recurrent Neural Network Models: Recurrent neural networks, or RNNs, are those types of neural networks that use an output of the network from a prior step as an input in attempt to automatically learn across sequence data.
LSTM: The LSTM neural network can be used for univariate time series forecasting.
CNN LSTM: We have seen that the CNN model is capable of automatically learning and extracting features from the raw sequence data without scaling or differencing.
ConvLSTM: It is possible to perform a convolutional operation as part of the read of the input sequence within each LSTM unit.