Can you explain what is meant by deep learning in the field of machine learning?

Deep learning is a subset of machine learning that uses multi-layered neural networks to automatically extract features from data and build complex models. Unlike traditional machine learning, where features are often manually created, deep learning allows models to learn to represent data at different levels of abstraction.

For example, in an image recognition task, the initial layers of the network may identify simple elements (edges, corners), while deeper layers recognize complex objects (faces, objects).

A simple neural network example in Python using the Keras library:

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

model = Sequential([
    Dense(64, activation='relu', input_shape=(100,)),
    Dense(10, activation='softmax')
])

model.compile(optimizer='adam', loss='categorical_crossentropy')