Data: Training Dataset has 60K samples, and test dataset has 10K samples. Each sample or image is 28*28 grayscale image. The dataset has 10 classes.
This is a Classification problem. You can import dataset from the following link to replicate the same results and follow along the experiement. We'll use Keras to build a Dense Neural Network to solve this problem. We'll also explore how to use Keras' Sequential, and Functional APIs to build our Neural Network.
Dependencies: : You'll need to install below dependencies to run this project.
- numpy: 1.18.1
- pandas: 1.0.1
- matplotlib: 3.5.3
- sklearn: 0.22.1
- tensorflow
- keras
The code has been tested on Windows system. It should work well on other distributions but has not yet been tested.
In case of any issue with installation or otherwise, please contact me on Linkedin
- Explore MNIST dataset.
- How to use Keras' Sequential API to build a Dense Neural Network?
- How to use Keras' Functional API to build a Dense Neural Network?
- How to define Number of neurons at Input, Hidden, and Output layers?
- How to calculate total number of parameters?
- How to plot total number of parameters?
- How to use callbacks for EarlyStopping to save model's weights at different checkpoints or epochs?
If you have a Data Science mini-project that you'd like to share, please follow the guidelines in CONTRIBUTING.md.
Please adhere to our Code of Conduct in all your interactions with the project.
This project is licensed under the MIT License.
For questions or inquiries, feel free to contact me on Linkedin.
I’m a seasoned Data Scientist and founder of TowardsMachineLearning.Org. I've worked on various Machine Learning, NLP, and cutting-edge deep learning frameworks to solve numerous business problems.