JA8. Unsupervised Learning – Clustering¶
Statement¶
Your learning journal entry must be a reflective statement that considers the following questions:
1. Describe what you did¶
This was the last week of this course, it was about the clustering as an example of unsupervised learning. I started the week as usual by trying the self-quiz then I started to read the text; the text size for this week was a bit overwhelming and I was able to skim it and take some notes. Later, I did the discussion assignments, and finally I am preparing the learning journal.
2. Describe your reactions to what you did¶
Apart from the overwhelming size of the required readings, the discussion forum question and the self quiz were straight foreword, I was surprised by my classmates responses as they covered the topics from very different angles and they provided tons of interesting diagrams and resources.
3. Describe any feedback you received or any specific interactions you had. Discuss how they were helpful¶
I have not received any feedback worth mentioning, possibly due to my late participation in the discussion forums. However, I have been able to learn from the posts of other students as mentioned above.
4. Describe your feelings and attitudes¶
The discussion forum prompt was about explaining the hierarchical clustering, describing an algorithm to implement it, and speaking about the role of dendrograms. I was able to manage the assignment, and I saw lots of interesting posts from my classmates. But these kind of open questions have two sides one that make them open to interpretation and thus hard to answer, and the other is giving the student the freedom to go far and beyond into the topic. I think my answer was average, but some people did a great job.
5. Describe what you learned¶
I learned about the concepts of unsupervised learning and how it is different from what we have used to though out the course. I also learned about the problem of clustering and how it differs from the classification and regression problems. I learned about the different types of clustering and how they are implemented. Finally, I learned about the role of dendrograms in the hierarchical clustering (Sayad, 2010). I also learned about K-means clustering and how to select the value of K (Pham, Dimov, & Nguyen, 2005).
6. What surprised me or caused me to wonder?¶
The difference between the classification and clustering problem was surprising to me, I thought they are the same. But I learned that the classification problem is about predicting the class of a new data point based on the training data, while the clustering problem is about grouping the training data into classes based on shared characteristics (GeeksForGeeks, 2023).
7. What happened that felt particularly challenging? Why was it challenging to me?¶
Understanding the K-means clustering algorithm was challenging to me, I had to read the text which was not clear and then search the internet for more resources to understand it. I think the reason for this is that my math background is not strong enough.
8. What skills and knowledge do I recognize that I am gaining?¶
I gained theoretical knowledge about supervised learning, clustering problem and the different types of clustering algorithms. I also gained practical knowledge about how to implement the K-means clustering algorithm.
9. What am I realizing about myself as a learner?¶
I realized that the period of 6 weeks that we used to supervised learning is was not short to the point that I got used to it and it is hard for me to learn a new completely different topic in just one week.
10. In what ways am I able to apply the ideas and concepts gained to my own experience?¶
I think the clustering problem is very useful in my field of work, I can use it to group my customers based on their characteristics and then target each group with a different marketing campaign.
11. Describe one important thing that you are thinking about in relation to the activity¶
As I said the period of one week is not enough to do anything; I would suggest to editing the course to be only about supervised learning and to add a new course about unsupervised learning or add it to the next course CS4408.
References¶
- Sayad S. (2010). Hierarchical Clustering. https://saedsayad.com/clustering_hierarchical.htm
- Pham, D. T., Dimov, S. S., & Nguyen, C. D. (2005). Selection of K in K-means clustering. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 219(1), 103-119. Available from http://www.ee.columbia.edu/~dpwe/papers/PhamDN05-kmeans.pdf
- GeeksForGeeks. (2023). Classification vs Clustering. https://www.geeksforgeeks.org/ml-classification-vs-clustering/