https://github.com/cyprianfusi/predict-fuel-efficiency-using-linear-regression-with-tensorflow
This project demonstrates the power of introducing non-linearity in neural network models to capture relevant patterns in data
https://github.com/cyprianfusi/predict-fuel-efficiency-using-linear-regression-with-tensorflow
keras linear-regression neural-networks pandas programming python3 tensorflow2
Last synced: about 1 month ago
JSON representation
This project demonstrates the power of introducing non-linearity in neural network models to capture relevant patterns in data
- Host: GitHub
- URL: https://github.com/cyprianfusi/predict-fuel-efficiency-using-linear-regression-with-tensorflow
- Owner: CyprianFusi
- Created: 2025-01-12T08:59:56.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-12T16:26:59.000Z (over 1 year ago)
- Last Synced: 2025-03-02T04:43:10.385Z (over 1 year ago)
- Topics: keras, linear-regression, neural-networks, pandas, programming, python3, tensorflow2
- Language: Jupyter Notebook
- Homepage:
- Size: 630 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Predict-fuel-efficiency-using-Linear-Regression-with-tensorflow
This project demonstrates the **power of introducing non-linearity** in neural network models to capture relevant patterns in data.
We are going to make use of modules and functions from the Keras API to train a linear regression model to predict fuel efficiency from features such as `cylinders, displacement, horsepower`, and `weight`. We shall train both shallow and deep neural network models and compare them. We use non-linear `ReLU` activation function in the hidden layers of a neural network model to capture the non-linear relationships between features and target.
## Dataset
We will use the classic [Auto MPG](https://archive.ics.uci.edu/ml/datasets/auto+mpg) dataset and demonstrates how to build models to predict the fuel efficiency of the late-1970s and early 1980s automobiles. The dataset is also available from the [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/).