Types of Features Representation Learning
Features Representation Learning:
An algorithm is a systematic way of repeatedly applying mathematical operations to a representation in order to achieve some computational goal. Asking what algorithms a representation supports, therefore, is a matter of asking what mathematical operations can be meaningfully applied to it.
The performance of machine learning methods is heavily dependent on the choice of data representation on which they are applied. For that reason, much of the actual effort in deploying machine learning algorithms goes into the design of pre-processing pipelines and data transformation. The result in representation of the data that can support effective machine learning. Such feature engineering is important but labor-intensive and highlights the weakness of current learning algorithms. Their inability to extract and organize the discriminative information from the data.
Feature Engineering is a way to take advantage of human ingenuity and prior knowledge of compensate for that weakness. In order to expand the scope and ease of applicability of machine learning. It would be highly desirable to make learning algorithms less dependent on feature engineering. So that novel applications could be constructed faster, and more importantly to make progress towards Artificial Intelligence (AI).
Types of Features Representation Learning:
Features Representation Learning divided into two major categories:
1. Supervised Features Representation Learning: It is learning features from labelled data. The data label allows the system to compute an error term, the degree to which the system fails to produce the label, which can then be used as feedback to correct the learning process.
2. Unsupervised Features Representation Learning: It is learning features from unlabeled data. The goal of unsupervised feature learning is often to discover low-dimensional features that captures some structure underlying the high-dimensional input data. When the feature learning is performed in an unsupervised way, it enables a form of semi-supervised learning where features learned from an unlabeled dataset are then employed to improve performance in a supervised setting with labelled data.