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

CodeSignal

Introduction to RNNs for Time Series Analysis

via CodeSignal

Go to class Write review

Overview

Learn to build and evaluate RNN, LSTM, and GRU models for time series forecasting using PyTorch. You'll work with univariate and multivariate data, implement classification tasks, and apply advanced techniques to boost forecasting performance.

Syllabus

  • Unit 1: Introduction to Recurrent Neural Networks (RNNs) with PyTorch
    • Loading and Formatting Time Series Data with Pandas
    • Visualizing Time Series Data
  • Unit 2: Data Preparation for RNNs
    • Standardizing Time Series Data with StandardScaler
    • Normalizing Time Series Data with MinMaxScaler for RNNs
    • Creating Sequence Data for RNN Time Series Forecasting
    • Time Series Data Preprocessing for RNN Training
  • Unit 3: Building a Basic RNN Model with PyTorch
    • Implementing an RNN Model for Time Series Prediction in PyTorch
    • Training a Recurrent Neural Network for Time Series Analysis
    • Visualizing RNN Training Loss Curves
    • Evaluating RNN Model Performance with RMSE and Visualization
    • Exploring the Impact of Epoch Count on RNN Model Performance
  • Unit 4: Extending Recurrent Neural Networks for Time Series Classification with PyTorch
    • Preprocessing Airline Passenger Data for Binary Trend Classification
    • Converting Binary Labels to One-Hot Encoded Format in PyTorch
    • Building an RNN Classifier for Time Series Data
    • Training and Evaluating an RNN for Time Series Classification

Reviews

Start your review of Introduction to RNNs for Time Series Analysis

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.