Figura 1. Problema di classificazione non lineare. Una funzione lineare non può separa in modo pulito tutti i pallini blu da quelli arancioni.
"Non lineare" significa che non puoi prevedere con precisione un'etichetta con un modello del formato \(b + w_1x_1 + w_2x_2\). In altre parole, la "superficie di decisione" non è una linea.
Tuttavia, se eseguiamo un'intersezione di caratteristiche sulle nostre caratteristiche $x_1$ e $x_2$, possiamo rappresentare la relazione non lineare tra le due caratteristiche utilizzando un modello lineare: $b + w_1x_1 + w_2x_2 + w_3x_3$ dove $x_3$ è l'intersezione di caratteristiche tra $x_1$ e $x_2$:
Figura 2. Aggiungendo l'incrocio di caratteristiche x1x2, il modello lineare può apprendere una forma iperbolica che separa i punti blu da quelli arancioni.
Consideriamo ora il seguente set di dati:
Figura 3. Un problema di classificazione non lineare più difficile.
Potresti anche ricordare dagli esercizi sulle intersezioni delle caratteristiche che determinare le intersezioni delle caratteristiche corrette per adattare un modello lineare a questi dati ha richiesto un po' più di impegno e sperimentazione.
E se non dovessi eseguire personalmente tutte queste sperimentazioni? Le reti neurali sono una famiglia di architetture di modelli progettate per trovare pattern non lineari nei dati. Durante l'addestramento di una rete neurale, model automaticamente Apprende gli incroci di caratteristiche ottimali da eseguire sui dati di input per ridurre al minimo o una perdita di dati.
Nelle sezioni seguenti, esamineremo più da vicino come funzionano le reti neurali.
[[["Facile da capire","easyToUnderstand","thumb-up"],["Il problema è stato risolto","solvedMyProblem","thumb-up"],["Altra","otherUp","thumb-up"]],[["Mancano le informazioni di cui ho bisogno","missingTheInformationINeed","thumb-down"],["Troppo complicato/troppi passaggi","tooComplicatedTooManySteps","thumb-down"],["Obsoleti","outOfDate","thumb-down"],["Problema di traduzione","translationIssue","thumb-down"],["Problema relativo a esempi/codice","samplesCodeIssue","thumb-down"],["Altra","otherDown","thumb-down"]],["Ultimo aggiornamento 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,["| **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)"]]