Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/anushadatta/neural-networks-deep-learning
🔗 Music Genre Classification & HDB Price Prediction.
https://github.com/anushadatta/neural-networks-deep-learning
keras neural-networks tensorflow
Last synced: 7 days ago
JSON representation
🔗 Music Genre Classification & HDB Price Prediction.
- Host: GitHub
- URL: https://github.com/anushadatta/neural-networks-deep-learning
- Owner: anushadatta
- Created: 2021-12-29T09:34:33.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2022-01-08T17:59:48.000Z (about 3 years ago)
- Last Synced: 2024-12-11T22:28:24.403Z (2 months ago)
- Topics: keras, neural-networks, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 4.78 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Neural Networks & Deep Learning
> CZ4042 Neural Networks & Deep Learning \
> School of Computer Science and Engineering \
> Nanyang Technological UniversityThis repository consists of CZ4042 Assignment 1, which is composed of the following problem sets:
## (A) Music Genre Classification
AIM: Perform music genre classification by predicting the genre label for a given audio file.
DATASET: GTZAN dataset
* ```features_30_sec.csv```
* 1000 audio tracks, 30 seconds each
* Audio tracks preprocessed into 57 features
* Genres (10 labels): blues, classical, country, disco, hip-hop, jazz, metal, pop, reggae and rock
* 1 pattern: filename + audio length + 57 features + label/genre## (B) HDB Price Prediction
AIM: (i) Perform retrospective prediction of HDB housing prices (resale_price), (ii) Identify the most important features that contributed to the prediction (Recursive Feature Elimination)
DATASET: Publicly available data on HDB flat prices in Singapore, obtained from data.gov.sg on 5th August 2021
* ```hdb_price_prediction.csv```
* Original feature set modified with other datasets to add informative features, as outlined in ```Assignment1.pdf```