1. Learn
    2. /
  2. Courses
    3. /
  3. Introduction to Deep Learning with PyTorch
  • 1

    Introduction to PyTorch, a Deep Learning Library

    Free

    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.

  • 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.

  • 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.

  • 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.

Initializing

Exercise

Building a binary classifier in PyTorch

Recall that a small neural network with a single linear layer followed by a sigmoid function is a binary classifier. It acts just like a logistic regression.

In this exercise, you'll practice building this small network and interpreting the output of the classifier.

The torch package and the torch.nn package have already been imported for you.

Instructions 1/2

undefined XP
    1
    2
  • Create a neural network that takes a tensor of dimensions 1x8 as input, and returns an output of the correct shape for binary classification.
  • Pass the output of the linear layer to a sigmoid, which both takes in and return a single float.