Figura 1: Problema de clasificación no lineal. Una función lineal no puede
separar limpiamente todos los puntos azules de los puntos anaranjados.
"No lineal" significa que no se puede predecir con exactitud una etiqueta con una
con el formato \(b + w_1x_1 + w_2x_2\). En otras palabras, la "superficie de decisión" no es una línea.
Sin embargo, si hacemos una combinación de atributos en los atributos $x_1$ y $x_2$, podemos
luego representar la relación no lineal entre los dos atributos con un
modelo lineal:
$b + w_1x_1 + w_2x_2 + w_3x_3$, donde $x_3$ es la combinación de atributos
$x_1$ y $x_2$:
Figura 2: Cuando se agrega la combinación de atributos x1x2, el modelo lineal puede aprender una forma hiperbólica que separa los puntos azules de los anaranjados.
Ahora, considera el siguiente conjunto de datos:
Figura 3: Un problema de clasificación no lineal más difícil.
Es posible que también lo recuerdes de los ejercicios de combinación de atributos.
que determinar las combinaciones de atributos correctas
para ajustar un modelo lineal a estos datos
requería un poco más de esfuerzo y experimentación.
Pero ¿qué pasaría si no tuvieras que hacer toda esa experimentación por tu cuenta?
Las redes neuronales son un conjunto
de arquitecturas de modelos diseñadas para encontrar
nonlinear
patrones en los datos. Durante el entrenamiento de una red neuronal, el modelo aprende automáticamente las combinaciones de atributos óptimas que se deben realizar en los datos de entrada para minimizar la pérdida.
En las siguientes secciones, analizaremos con más detalle cómo funcionan las redes neuronales.
[null,null,["Última actualización: 2025-07-27 (UTC)"],[[["\u003cp\u003eThis module explores neural networks, a model architecture designed to automatically identify nonlinear patterns in data, eliminating the need for manual feature cross experimentation.\u003c/p\u003e\n"],["\u003cp\u003eYou will learn the fundamental components of a deep neural network, including nodes, hidden layers, and activation functions, and how they contribute to prediction.\u003c/p\u003e\n"],["\u003cp\u003eThe module covers the training process of neural networks, using the backpropagation algorithm to optimize predictions and minimize loss.\u003c/p\u003e\n"],["\u003cp\u003eAdditionally, you will gain insights into how neural networks handle multi-class classification problems using one-vs.-all and one-vs.-one approaches.\u003c/p\u003e\n"],["\u003cp\u003eThis module builds on prior knowledge of machine learning concepts such as linear and logistic regression, classification, and working with numerical and categorical data.\u003c/p\u003e\n"]]],[],null,["# Neural networks\n\n| **Estimated module length:** 75 minutes\n| **Learning objectives**\n|\n| - Explain the motivation for building neural networks, and the use cases they address.\n| - Define and explain the function of the key components of a deep neural network architecture:\n| - **[Nodes](/machine-learning/glossary#node-neural-network)**\n| - **[Hidden layers](/machine-learning/glossary#hidden_layer)**\n| - **[Activation functions](/machine-learning/glossary#activation_function)**\n| - Develop intuition around how neural network predictions are made, by stepping through the inference process.\n| - Build a high-level intuition of how neural networks are trained, using the backpropagation algorithm.\n| - Explain how neural networks can be used to perform two types of multi-class classification: one-vs.-all and one-vs.-one.\n| **Prerequisites:**\n|\n| This module assumes you are familiar with the concepts covered in the\n| following modules:\n|\n| - [Introduction to Machine Learning](/machine-learning/intro-to-ml)\n| - [Linear regression](/machine-learning/crash-course/linear-regression)\n| - [Logistic regression](/machine-learning/crash-course/logistic-regression)\n| - [Classification](/machine-learning/crash-course/classification)\n| - [Working with numerical data](/machine-learning/crash-course/numerical-data)\n| - [Working with categorical data](/machine-learning/crash-course/categorical-data)\n| - [Datasets, generalization, and overfitting](/machine-learning/crash-course/overfitting)\n\nYou may recall from the\n[Feature cross exercises](/machine-learning/crash-course/categorical-data/feature-cross-exercises)\nin the [Categorical data module](/machine-learning/crash-course/categorical-data),\nthat the following classification problem is nonlinear:\n**Figure 1.** Nonlinear classification problem. A linear function cannot cleanly separate all the blue dots from the orange dots.\n\n\"Nonlinear\" means that you can't accurately predict a label with a\nmodel of the form \\\\(b + w_1x_1 + w_2x_2\\\\). In other words, the\n\"decision surface\" is not a line.\n\nHowever, if we perform a feature cross on our features $x_1$ and $x_2$, we can\nthen represent the nonlinear relationship between the two features using a\n[**linear model**](/machine-learning/glossary#linear-model):\n$b + w_1x_1 + w_2x_2 + w_3x_3$ where $x_3$ is the feature cross between\n$x_1$ and $x_2$:\n**Figure 2.** By adding the feature cross *x* ~1~*x* ~2~, the linear model can learn a hyperbolic shape that separates the blue dots from the orange dots.\n\nNow consider the following dataset:\n**Figure 3.** A more difficult nonlinear classification problem.\n\nYou may also recall from the [Feature cross exercises](/machine-learning/crash-course/categorical-data/feature-cross-exercises)\nthat determining the correct feature crosses to fit a linear model to this data\ntook a bit more effort and experimentation.\n\nBut what if you didn't have to do all that experimentation yourself?\n[**Neural networks**](/machine-learning/glossary#neural_network) are a family\nof model architectures designed to find\n[**nonlinear**](/machine-learning/glossary#nonlinear)\npatterns in data. During training of a neural network, the\n[**model**](/machine-learning/glossary#model) automatically\nlearns the optimal feature crosses to perform on the input data to minimize\nloss.\n\nIn the following sections, we'll take a closer look at how neural networks work.\n| **Key terms:**\n|\n| - [Activation function](/machine-learning/glossary#activation_function)\n| - [Hidden layer](/machine-learning/glossary#hidden_layer)\n| - [Linear model](/machine-learning/glossary#linear-model)\n| - [Model](/machine-learning/glossary#model)\n| - [Neural network](/machine-learning/glossary#neural_network)\n| - [Nodes](/machine-learning/glossary#node-neural-network)\n- [Nonlinear](/machine-learning/glossary#nonlinear) \n[Help Center](https://support.google.com/machinelearningeducation)"]]