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

CodeSignal

Handling Multivariate Time Series with RNNs

via CodeSignal

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: Handling Multivariate Time Series with RNNs Using PyTorch
    • Preparing Air Quality Time Series Data by Creating DateTime Columns and Handling Missing Values
    • Cleaning Air Quality Data for Time Series Analysis
    • Setting DateTime as Index for Time Series Analysis
    • Visualizing NO2 Levels in Time Series Data
  • Unit 2: Preparing Data for RNNs with PyTorch
    • Feature Selection and Normalization for Air Quality RNN Model
    • Creating Time Sequences for RNN Input
  • Unit 3: Introduction to RNNs for Multivariate Time Series with PyTorch
    • Implementing an RNN Model for Multivariate Time Series Forecasting
    • RNN Parameter Calculation and Verification
    • Training an RNN Model for Time Series Forecasting
    • Enhancing RNN Model Architecture
  • Unit 4: Evaluating RNN Performance with PyTorch
    • Evaluating RNN Model Performance Using Root Mean Squared Error
    • Visualizing RNN Temperature Predictions vs Actual Values
    • Visualizing and Analyzing RNN Training Loss Curves

Reviews

Start your review of Handling Multivariate Time Series with RNNs

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.