Not all data can easily be represented as fixed-length vectors. For instance, images from the internet may have different resolutions, and text data, such as customer reviews, can vary significantly in length. Modern deep learning models have a major advantage over traditional methods in their comparative grace when handling varying-length data.

Varying-Length Data

Fixed-length data refers to datasets where every example is characterized by the exact same number of numerical features. When inputs are structured this way, they are often referred to as fixed-length vectors, and this constant length is known as the dimensionality of the data. Working with fixed-length inputs is typically convenient for machine learning models as it provides a uniform structure, contrasting with varying-length data forms like text or unstandardized images.

Fixed-Length Data

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 $$200 	imes 200 	imes 3 = 120000$$.

Claude

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

In machine learning, image data is often represented numerically. 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.

Image Data Representation Example

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.

Learn Before

Related

Learn After