In machine learning, image data is often represented numerically as a set of features. For instance, a color photograph can be represented as three grids of numerical values corresponding to the brightness of red, green, and blue light at each pixel location. Consequently, a $$ 200 \times 200 $$ pixel color image consists of $$ 200 \times 200 \times 3 = 120000 $$ numerical features.

Claude

Google

In a machine learning dataset, a feature (also referred to as an input or covariate) is an individual, measurable attribute of a given data point. A model relies on these numerical representations to make its predictions.

Machine Learning Feature

Dive into Deep Learning

In supervised learning problems, a label, also known as a target, is a special attribute of an example that a model aims to predict. It represents the known outcome or ground truth that is not part of the model's input features.

Machine Learning Label

Electronic health records provide a classic example of tabular data used in machine learning. For example, when predicting whether a patient will survive the next 30 days, the features might include a set of readily available attributes such as age, vital signs, comorbidities, current medications, and recent procedures. The label used for training the model would be a binary value indicating if the patient survived within that 30-day period.

Electronic Health Record Data Example

One of the most significant advantages of deep learning is its ability to replace the labor-intensive process of manual feature engineering. In traditional machine learning, domain experts crafted specific algorithms to transform raw perceptual data into feature vectors. Deep learning replaces these domain-specific preprocessing steps with automatically tuned filters that are learned jointly from the data, yielding superior accuracy and providing a unified approach across diverse fields.

Automated Feature Engineering

When machine learning inputs are structured as fixed-length vectors, the constant length of these vectors—meaning the exact number of numerical features—is defined as the dimensionality of the data. For instance, a $$200 	imes 200$$ pixel color image represented by red, green, and blue values has a dimensionality of $$200 	imes 200 	imes 3 = 120000$$.

Data Dimensionality

In machine learning domains such as natural language processing, computational advertising, and personalized collaborative filtering, it is common to encounter sparse features. These are features that occur only infrequently in the data, meaning that the parameters associated with them only receive meaningful updates during training when those rare features are actually observed.

Learn Before

Related