This project involves a series of practical experiments conducted on the Waveform Dataset (Breiman & Stone, 1988) as a part of the Introduction to Machine Learning course. The primary focus of these experiments is to apply theoretical concepts learned in the course and to specifically address the limitations of the k-nearest neighbor (kNN) algorithm.
- To understand and apply the theoretical concepts of Machine Learning.
- To explore the Waveform Dataset and its characteristics.
- To identify and address the limitations of the k-nearest neighbor (kNN) algorithm in the context of this dataset.
The experiments were structured to first understand the dataset and then apply the kNN algorithm, followed by an analysis of its performance and limitations. Various strategies were then implemented to overcome these limitations.
- Python 3.11
- Libraries: numpy, pandas, matplotlib, sklearn
- Dataset: Waveform Dataset (Breiman & Stone, 1988)
- Describe the steps to run the experiments.
- Include code snippets or command-line instructions if applicable.
- Summarize the key findings from the experiments.
- Discuss how the limitations of the kNN algorithm were addressed.
- Reflect on the learning outcomes from these experiments.
- Suggest potential areas for further research or improvement.
- Breiman, L., & Stone, C.J. (1988). Classification and Regression Trees. Wadsworth.