Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Handling Multivariate Time Series with RNNs

Go to class Write review

Overview

This course extends the concepts from the first course by introducing multiple time series inputs. It covers how to preprocess, structure, and train RNN models using **two related time series features** from the **Air Quality dataset**. It also includes model evaluation techniques to assess forecasting accuracy.

Syllabus

Unit 1: Understanding and Preprocessing Multivariate Time Series

Creating a DateTime Index for Time Series
Handling Missing Values in Time Series
Setting DateTime as Time Series Index
Visualizing Time Series Pollution Patterns

Unit 2: Preparing Data for RNNs

Feature Selection and Data Normalization
Creating Sequences for RNN Input
Reshaping Sequences for RNN Input
Chronological Train Test Split Implementation

Unit 3: Building an RNN for Multivariate Time Series

Building Your First RNN Architecture
Understanding RNN Parameter Calculations
Compiling and Training Your RNN Model
Experimenting with RNN Architecture Complexity

Unit 4: Evaluating Multivariate RNN Performance

Calculating RMSE for Model Evaluation
Visualizing RNN Predictions with Matplotlib
Visualizing RNN Training Loss Patterns

Reviews

Start your review of Handling Multivariate Time Series with RNNs