Module4

Module4. Wavelet Denoising + Auto Encoder Model + RNN Prediction Model for Price Prediction

Will be released after Module3

Goal

• Learn how to implement Wavelet Denoising + Auto Encoder Model + RNN Prediction models using Tensorflow Keras API on Google Colab

Modules

• M4.1 Wavelet Stacked Autoencoder LSTM

  • [Reading] Wavelet Stacked Autoencoder LSTM

• M4.2 Wavelet Transform to Denoise the Data

  • [Video] Understanding Wavelets, Part 1: What Are Wavelets (5min)
  • [Video] Understanding Wavelets, Part 2: Types of Wavelet Transforms (5min)
  • [Video] Understanding Wavelets, Part 3: An Example Application of the Discrete Wavelet Transform (5min)
  • [Video] Understanding Wavelets, Part 4: An Example Application of Continuous Wavelet Transform (5min)
  • [Hands-on-Labs] Wavelets in Python [Code]

• M4.3 Keras Functional API and Stacked Autoencoders

  • [Reading] A Gentle Introduction to the Keras Functional API
  • [Hands-on-Labs] Autoencoders for Feature Extraction [Code]

• M4.4 Stacked Autoencoders to Extract Features from Data

  • [Assignment] Stacked Autoencoders to Extract Features from Data [Problem] [Solution]

• M4.5 Final Neural Network Model

  • [Hands-on-Labs] Stacked Autoencoder LSTM [Code]
  • [Assignment] Write Your Own Neural Network Model for Financial Time Series Prediction [Problem]

• M4.6 Assignment

• M4.7 Slack Discussion

Q&A

• Module 4. Wavelet Denoising + Auto Encoder Model + RNN Prediction Model for Price Prediction

What's next?

The beauty of this model is the once the construction is understood, the individual models can be swapped out for the best model there is. So over time the actual models used here will be different but the core framework will still be the same.

References

• A deep learning framework for financial time series using stacked autoencoders and long-short term memory, July 2017
• AlphaAI: Multilayer neural network architecture for stock return prediction, Oct 2018