Learning is the process by which a model is constructed, the model describes a set of observations. The more compact the model, the better the learning process is considered. This is manifest in the ability of the model to predict and generalize (out-of-sample) data. But let's not confuse learning with classification. Again, the essence of learning is the model construction and the condensed representation of the observations. So how many observations, data elements, are required to construct a model? [Nassim Taleb addresses this question here: https://arxiv.org/pdf/1802. 05495.pdf ] The typical answer is for a Gaussian/normal distribution, 30 observations, simple. We construct a model of the mean and variance of the data by calculating the average and variance from our 30 sample observations. Clearly this is not true in all cases, we do not always have simple normal distributions. And in more complex case we would require more obs...