Supervised and Unsupervised machine learning

SUPERVISED MACHINE LEARNING

Supervised machine learning takes a known set of input data and known response to the data, and seeks to build a predictor model that generates responsible predictions for the response to new data.  In order to solve a given problem of supervised learning, one has to perform the following steps

First step is to determine the type of training examples. Before doing anything else, the user should decide what kind of data is to be used as a training set. In the case of handwriting analysis, for example, this might be a single hand-written character, an entire hand written word, or an entire line of handwriting.

Second step is to gather a training set. The training set needs to be representative of the real-world use of the function. Thus, a set of input objects is gathered and corresponding outputs are also gathered, either from human experts or from measurements.

Thirds step is to determine the input feature representation of the learned function. The accuracy of the learned function depends strongly on how the input object is represented. Typically, the input object is transformed into a feature vector, which contains a number of features that are descriptive of the object. The number of features should not be too large, because of the curse of dimensionality, but should contain enough information to accurately predict the output.

Fourth step is to determine the structure of the learned function and corresponding learning algorithm.

Fifth step is to complete the design, namely to run the learning algorithm on the gathered training set. Some supervised learning algorithms require the user to determine certain control parameters. These parameters may be adjusted by optimizing performance on a subset of the training set, or via cross-validation.

The sixth step is to evaluate the accuracy of the learned function. After parameter adjustment and learning, the performance of the resulting function should be measured on a test set that is separate from the training set.

So far scientist have developed many supervised learning algorithms and each of them have some advantages and weaknesses. In general there is no supervised learning algorithm that can work on every supervised learning problems. 

UNSUPERVISED MACHINE LEARNING

There are many methods of unsupervised machine learning but one that is most important and used in field of sensor development is principle component analysis. Principle component analysis or shortly PCA is common method of unsupervised machine learning that has found multiple applications in the field such as facial recognition and image comparison. 

Here is a short video about PCA.

It is a common method of finding patterns in high dimensional data. The aim is the achievement of lower dimensional representation and visualization of the collected data in terms of scores on (uncorrelated) principle components, a so-called “score plot”.

This method enables the interpretation of a large data set using a smaller number of components. Because patterns in data can be hard to find in high-dimension data, PCA is a powerful tool for data analysis.