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

CodeSignal

Time Series Forecasting with LSTMs

via CodeSignal

Go to class Write review

Overview

This course focuses on LSTM networks, a powerful extension of RNNs that handle long-term dependencies better than simple RNNs. Learners will build, optimize, and evaluate LSTM models for time series forecasting.

Syllabus

  • Unit 1: Introduction to Time Series Forecasting with LSTMs
    • Tracking Data Shapes During Preprocessing
    • Exploring Sequence Length Impact on Data
    • Building Your First LSTM Model
    • Exploring LSTM Activation Functions
  • Unit 2: Building an LSTM for Time Series Forecasting
    • Explicit Input Layers for LSTM Models
    • Adjusting LSTM Layer Complexity
    • Evaluating LSTM Models with RMSE
    • Impact of Training Duration on LSTMs
  • Unit 3: Evaluating and Visualizing LSTM Model Performance
    • Calculating RMSE for Model Comparison
    • Adding MAE to Model Evaluation
    • Implementing MAPE for Percentage Error Analysis
    • Enhancing LSTM Visualization for Better Insights
  • Unit 4: Optimizing LSTM Performance for Time Series Forecasting
    • Preventing Overfitting with Dropout Layers
    • Applying L1 and L2 Regularization Techniques
    • Stabilizing LSTM Training with Batch Normalization
    • Implementing Early Stopping for Efficient Training

Reviews

Start your review of Time Series Forecasting with LSTMs

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.