Pular para o conteúdo principal
Página inicialArtificial IntelligenceIntroduction to Deep Learning with PyTorch

Introduction to Deep Learning with PyTorch

Learn the power of deep learning in PyTorch. Build your first neural network, adjust hyperparameters, and tackle classification and regression problems.

Comece O Curso Gratuitamente
4 Horas16 Videos50 Exercicios
18.144 AprendizesTrophyDeclaração de Realização

Crie sua conta gratuita

GoogleLinkedInFacebook

ou

Ao continuar, você aceita nossos Termos de Uso, nossa Política de Privacidade e que seus dados são armazenados nos EUA.
GroupTreinar 2 ou mais pessoas?Experimente o DataCamp For Business

Amado por alunos de milhares de empresas


Descrição do Curso

Introduction to Deep Learning with PyTorch

Deep learning is everywhere: in smartphone cameras, voice assistants, and self-driving cars. It has even helped discover protein structures and beat humans at the game of Go. In this course, you will discover this powerful technology and learn how to leverage it using PyTorch, one of the most popular deep learning libraries.

Train your first neural network

First, this course tackles the difference between deep learning and "classic" machine learning and will introduce neural networks. You will learn about the training process of a neural network and how to write a training loop. To do so, you will create loss functions for regression and classification problems and leverage PyTorch to calculate their derivatives.

Evaluate and improve your model

In the second half of this course, you will learn about the different hyperparameters you can adjust to improve your model. After learning about the different components of a neural network, you will be able to create larger and more complex architectures. To measure your model performances, you will leverage TorchMetrics, a PyTorch library for model evaluation. By the end of this course, you will be able to leverage PyTorch to solve classification and regression problems on both tabular and image data using deep learning.
Para Empresas

GroupTreinar 2 ou mais pessoas?

Obtenha acesso à biblioteca completa do DataCamp, com relatórios, atribuições, projetos e muito mais centralizados
Experimente O DataCamp for BusinessPara uma solução sob medida , agende uma demonstração.

Nas seguintes faixas

Aprendizagem profunda em Python

Ir para a trilha

Desenvolvimento de modelos de idiomas grandes

Ir para a trilha

Machine Learning Fundamentals with Python

Ir para a trilha
  1. 1

    Introduction to PyTorch, a Deep Learning Library

    Grátis

    Self-driving cars, smartphones, search engines... Deep learning is now everywhere. Before you begin building complex models, you will become familiar with PyTorch, a deep learning framework. You will learn how to manipulate tensors, create PyTorch data structures, and build your first neural network in PyTorch.

    Reproduzir Capítulo Agora
    Introduction to deep learning with PyTorch
    50 xp
    Machine learning vs. deep learning
    100 xp
    Creating tensors and accessing attributes
    100 xp
    Creating tensors from NumPy arrays
    100 xp
    Creating our first neural network
    50 xp
    Your first neural network
    100 xp
    Stacking linear layers
    100 xp
    Discovering activation functions
    50 xp
    Activate your understanding!
    50 xp
    The sigmoid and softmax functions
    100 xp
  2. 2

    Training Our First Neural Network with PyTorch

    To train a neural network in PyTorch, you will first need to understand the job of a loss function. You will then realize that training a network requires minimizing that loss function, which is done by calculating gradients. You will learn how to use these gradients to update your model's parameters, and finally, you will write your first training loop.

    Reproduzir Capítulo Agora
  3. 3

    Neural Network Architecture and Hyperparameters

    Hyperparameters are parameters, often chosen by the user, that control model training. The type of activation function, the number of layers in the model, and the learning rate are all hyperparameters of neural network training. Together, we will discover the most critical hyperparameters of a neural network and how to modify them.

    Reproduzir Capítulo Agora
  4. 4

    Evaluating and Improving Models

    Training a deep learning model is an art, and to make sure our model is trained correctly, we need to keep track of certain metrics during training, such as the loss or the accuracy. We will learn how to calculate such metrics and how to reduce overfitting using an image dataset as an example.

    Reproduzir Capítulo Agora
Para Empresas

GroupTreinar 2 ou mais pessoas?

Obtenha acesso à biblioteca completa do DataCamp, com relatórios, atribuições, projetos e muito mais centralizados

Nas seguintes faixas

Aprendizagem profunda em Python

Ir para a trilha

Desenvolvimento de modelos de idiomas grandes

Ir para a trilha

Machine Learning Fundamentals with Python

Ir para a trilha

Em outras faixas

Cientista de aprendizado de máquina com Python

Colaboradores

Collaborator's avatar
George Boorman
Collaborator's avatar
Amy Peterson
Collaborator's avatar
James Chapman

Audio Gravado Por

Maham Khan's avatar
Maham Khan
Maham Khan HeadshotMaham Khan

Senior Data Scientist, YouView TV

Veja Mais

O que os outros alunos têm a dizer?

Junte-se a mais de 14 milhões de alunos e comece Introduction to Deep Learning with PyTorch hoje mesmo!

Crie sua conta gratuita

GoogleLinkedInFacebook

ou

Ao continuar, você aceita nossos Termos de Uso, nossa Política de Privacidade e que seus dados são armazenados nos EUA.