https://github.com/mehrab-kalantari/multi-layer-perceptron-fmnist
Building a multi-layer perceptron on fashion MNIST dataset
https://github.com/mehrab-kalantari/multi-layer-perceptron-fmnist
deep-learning fashion-mnist mlp multi-layer-perceptron neural-network
Last synced: 7 months ago
JSON representation
Building a multi-layer perceptron on fashion MNIST dataset
- Host: GitHub
- URL: https://github.com/mehrab-kalantari/multi-layer-perceptron-fmnist
- Owner: Mehrab-Kalantari
- Created: 2023-09-06T16:17:40.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-09-06T16:29:15.000Z (about 2 years ago)
- Last Synced: 2025-01-16T09:42:28.958Z (9 months ago)
- Topics: deep-learning, fashion-mnist, mlp, multi-layer-perceptron, neural-network
- Language: Jupyter Notebook
- Homepage:
- Size: 45.9 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Multi-Layer Perceptron on Fashion MNIST Dataset
[Dataset on kaggle](https://www.kaggle.com/datasets/zalando-research/fashionmnist)
## Contents
### Data Cleaning
Reading the dataset and splitting target and input
### Data Preprocessing
* Scaling
* Encoding
### Modeling
Here we use a multi-layer perceptron with 2 hidden layers
* Callbacks: early stopping
* Input layer: 300 units with relu activation and 0.3 dropout
* Hidden layers: 2 hidden layers with relu activation, first layer has 50 units with 0.2 dropout and second layer has 10 units
* Output layer: 10 units with softmax activation
* Optimizer: adam
* Loss: categorical cross entropy
* Metric: categorical accuracy
### Evaluation
