Long Short-Term Memory networks, or LSTMs for short, can be applied to time series forecasting. There are many types of LSTM models that can be used for each specific type of time series forecasting problem. In this tutorial, you will discover how to develop a suite of LSTM models for a range of standard time […]
Type of Material:
Tutorial
Recommended Uses:
Can be used for in-class example or self-paced learning.
Technical Requirements:
Web browser
Identify Major Learning Goals:
How to develop LSTM models for univariate time series forecasting.
How to develop LSTM models for multivariate time series forecasting.
How to develop LSTM models for multi-step time series forecasting.
Target Student Population:
College General Ed, College Lower Division, College Upper Division, Professional
Prerequisite Knowledge or Skills:
Prior knowledge and experience with:
Univariate and multivariate time series forecasting problems
Long Short-Term Memory network models
Content Quality
Rating:
Strengths:
- In this single page tutorial, many types of Long Short Term Memory (LSTM) models are introduced, univariate, multivariate to multi-step models.
- It does not present the theories or maths behind the features in LSTM, but it attempts to explain the key terms involved in the topic. And then, it goes straight forward on the code in Python to deploy these features.
Concerns:
- On the topic of Multiple Parallel Series, the coding needed to be further explained to help to the reader to understand it on the multi-value output.
- Prerequisite knowledge and skills are not articulated for this tutorial.
Potential Effectiveness as a Teaching Tool
Rating:
Strengths:
- For each of the topics mentioned, it is illustrated with a concrete example. The examples are not complicated, but somehow a toy one, but they are able to highlight the main features of each of the model types.
- In each short tutorial page, it successfully presented the topics concisely with clear examples to contrast out the difference among them.
- Goals are easy to identify
- Given appropriate background, this information has the potential to promote conceptual understanding
- Increases potential for student learning in a narrowly focused area
Concerns:
Lacks identification of the intended audience
Ease of Use for Both Students and Faculty
Rating:
Strengths:
- It provides some cross-references on some terms in other pages of the website for further explanations or related topics.
- It does not goes with fancy graphics or animations, but the presentation of the webpage is easy to follow.
Concerns:
- It often refers to the book written by the author for some full explanations. At the same time, the page is already good enough to understand the key features presented.
- Lacks guidance on how to best use the proffered tutorial
Creative Commons:
Search by ISBN?
It looks like you have entered an ISBN number. Would you like to search using what you have
entered as an ISBN number?
Searching for Members?
You entered an email address. Would you like to search for members? Click Yes to continue. If no, materials will be displayed first. You can refine your search with the options on the left of the results page.
Searching for Members?
You entered an email address. Would you like to search for members? Click Yes to continue. If no, materials will be displayed first. You can refine your search with the options on the left of the results page.
