Deep learning vs Feature engineering

Why they differ

Deep learning finds useful inputs by itself from raw data; feature engineering has people build those inputs by hand.

Machine learning basics

Machine learning that uses neural networks with many stacked layers, the approach behind modern image, speech and language tools.

Formal

A kind of machine learning that trains neural networks with many layers, where each layer builds more general features from the output of the layer below, learned directly from raw data.

In plain English

Like a line of workers where the first notices edges, the next shapes, the next faces, and each passes a richer picture up the line.

In practice

A region's hospitals use a deep learning model, trained on hundreds of thousands of X-ray images, to mark possible fractures for a doctor to check.

Why it matters

It brought a large jump in what AI can do from about 2012, but the models need huge amounts of data and computing power, and their reasoning is very hard to explain.

Feature engineering

Machine learning basics

Turning raw records into useful inputs for a model, by picking, cleaning, combining and reshaping the facts it will read.

Formal

The work of building each feature from raw data using human knowledge of the problem, for example counting, grouping, turning text or dates into numbers and dropping unhelpful columns, done before or as part of model training.

In plain English

Like a cook who washes, peels and chops the vegetables before cooking, because the same pot gives a far better dish when what goes in is well prepared.

In practice

A bank building a model to spot card fraud does not hand it single payments; it adds new columns such as "number of payments in the last hour" and "distance from the customer's home".

Why it matters

On ordinary business tables, good inputs often matter more than the choice of model, and a careless step can leak the answer into the data.