Code-Alongs
What is a Code-Along?
Code-Alongs are live experiences taught by our instructors designed to prepare you for concepts found in the sprint challenges. They're your opportunity to work on complex job-ready problems in a live and engaging environment.
These sessions are 50 minutes in length and are offered seven days a week in the morning, afternoon, and evening. Because Code-Alongs delve deeper into a core competency, you will need to come to class prepared to have the best experience.
Ideal Code-Along Preparation Checklist
- Did you review the core competencies?
- Did you watch the guided projects?
- Did you finish your module projects?
Code-Along 1: LSTM Text Generation
This code-along focuses on building LSTM-based text generation models, reinforcing concepts from Module 1.
How to Prepare
- Review RNN and LSTM concepts from Module 1
- Review text preprocessing and sequence modeling
- Watch the guided project videos
- Complete your module projects before attending
Code-Along 2: Variational AutoEncoders (Optional - Legacy Material)
This session focuses on implementing variational autoencoders for generative modeling. Note that this code-along is based on legacy material and is optional, as it covers content not included in the current sprint modules. For additional context, you can review the legacy AutoEncoders material.
How to Prepare
- Review the legacy AutoEncoders material if interested
- Understand generative modeling concepts
Prepare for Success
The best Code-Along experiences happen when you are ready before coming to class. Your instructors created a starting point and a solution for each of your Code-Alongs to ensure you have what you need to succeed.
Make sure to review the relevant module materials before attending the code-along. This will help you get the most out of the session and be better prepared to tackle the challenges.
Additional Resources
LSTM and Text Generation
- TensorFlow: Text Generation with RNN
- Understanding LSTM Networks
- The Unreasonable Effectiveness of RNNs
- Keras LSTM Layer Documentation