📑 Deep Learning. Practice Project 1_0: Neural Networks for Regression
🌀 Homepage
🌀 Project List
🌀 Colaboratory Gist
🌀 Previous
🌀 Addition 1
🌀 Next
🌀 GitHub Pages
🌀 Instagram Posts
🌀 Pinterest Posts
In this project, we'll evaluate the performance and predictive power of neural networks in the sphere of regression tasks.
Models will be trained and tested on data collected from homes in suburbs of Boston, Massachusetts.
Origin: This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.
Creators: Harrison, D. and Rubinfeld, D.L.
Data Set Information: Concerns housing values in suburbs of Boston.
Attribute Information:
The Boston housing data was collected in 1978 and each of the
506 entries represents aggregated data about 14 features for homes from various suburbs.
✒️ Step 0. Import Libraries and Define Helpful Functions
💡 This cell does not work with Python 3.9.
✒️ Step 1. Load and Explore the Data
✒️ Step 2. Build Neural Networks with Keras Py
💡 This cell does not work with Python 3.9.
Multilayer Perceptron (MLP)
💡 This cell does not work with Python 3.9.
💡 This cell does not work with Python 3.9.
Convolutional Neural Network (CNN)
💡 This cell does not work with Python 3.9.
💡 This cell does not work with Python 3.9.
💡 This cell does not work with Python 3.9.
Recurrent Neural Network (RNN)
💡 This cell does not work with Python 3.9.
💡 This cell does not work with Python 3.9.
💡 This cell does not work with Python 3.9.
✒️ Step 3. Display Predictions of Keras Algorithms Py
💡 This cell does not work with Python 3.9.
✒️ Step 4. Compare with Sklearn Algorithms Py
✒️ Step 5. Neural Networks in R