A problem with many stochastic machine learning algorithms is that different runs of the same algorithm on the same data return different results. This means that when performing experiments to configure a stochastic algorithm or compare algorithms, you must collect multiple results and use the average performance to summarize the skill of the model. This […]
Dropout with LSTM Networks for Time Series Forecasting
Long Short-Term Memory (LSTM) models are a type of recurrent neural network capable of learning sequences of observations. This may make them a network well suited to time series forecasting. An issue with LSTMs is that they can easily overfit training data, reducing their predictive skill. Dropout is a regularization method where input and recurrent […]
How to Configure Multilayer Perceptron Network for Time Series Forecasting
It can be difficult when starting out on a new predictive modeling project with neural networks. There is so much to configure, and no clear idea where to start. It is important to be systematic. You can break bad assumptions and quickly hone in on configurations that work and areas for further investigation likely to […]
Instability of Online Learning for Stateful LSTM for Time Series Forecasting
Some neural network configurations can result in an unstable model. This can make them hard to characterize and compare to other model configurations on the same problem using descriptive statistics. One good example of a seemingly unstable model is the use of online learning (a batch size of 1) for a stateful Long Short-Term Memory […]
Stateful and Stateless LSTM for Time Series Forecasting with Python
The Keras Python deep learning library supports both stateful and stateless Long Short-Term Memory (LSTM) networks. When using stateful LSTM networks, we have fine-grained control over when the internal state of the LSTM network is reset. Therefore, it is important to understand different ways of managing this internal state when fitting and making predictions with […]
How to Use Features in LSTM Networks for Time Series Forecasting
The Long Short-Term Memory (LSTM) network in Keras supports multiple input features. This raises the question as to whether lag observations for a univariate time series can be used as features for an LSTM and whether or not this improves forecast performance. In this tutorial, we will investigate the use of lag observations as features […]
How to Use Timesteps in LSTM Networks for Time Series Forecasting
The Long Short-Term Memory (LSTM) network in Keras supports time steps. This raises the question as to whether lag observations for a univariate time series can be used as time steps for an LSTM and whether or not this improves forecast performance. In this tutorial, we will investigate the use of lag observations as time […]
How to Update LSTM Networks During Training for Time Series Forecasting
A benefit of using neural network models for time series forecasting is that the weights can be updated as new data becomes available. In this tutorial, you will discover how you can update a Long Short-Term Memory (LSTM) recurrent neural network with new data for time series forecasting. After completing this tutorial, you will know: […]
How to Tune LSTM Hyperparameters with Keras for Time Series Forecasting
Configuring neural networks is difficult because there is no good theory on how to do it. You must be systematic and explore different configurations both from a dynamical and an objective results point of a view to try to understand what is going on for a given predictive modeling problem. In this tutorial, you will […]
How to Seed State for LSTMs for Time Series Forecasting in Python
Long Short-Term Memory networks, or LSTMs, are a powerful type of recurrent neural network capable of learning long sequences of observations. A promise of LSTMs is that they may be effective at time series forecasting, although the method is known to be difficult to configure and use for these purposes. A key feature of LSTMs […]