Fuzzy C-means clustering

In Chapter 3, Learning from Big Data, we saw the k-means clustering algorithm, which is an iterative unsupervised algorithm that creates k clusters for a dataset based on the distance from a random centroid in the first iteration step. The centriods are calculated in each iteration to accommodate new data points. This process is repeated until the centriods do not change significantly after a point. As a result of the k-means clustering algorithm, we get discrete clusters with data points. Each data point either belongs to a cluster or it does not. There are only two states for a data point in terms of cluster membership. However, in real-world scenarios, we have data points that may belong to multiple clusters with different degrees of membership. The algorithms that create fuzzy membership instead of crisp membership for the data points within a cluster are termed soft-clustering algorithms. C-means clustering is one of the most popular algorithms, which is iterative...