Learn and practice PyTorch, a framework for developing deep learning models.

Become a Deep Learning Professional

In this module, we’ll be introduced to the fundamentals of PyTorch: autograd, model classes, datasets, data loaders, and more. We’ll develop models and understand them step-by-step. We'll understand the reasoning behind the code and how to avoid some common pitfalls and errors along the way.
By the time we finish this module, we’ll have a thorough understanding of the concepts and tools necessary to start developing and training our own models using PyTorch.

Deep Learning with PyTorch

It has a probability of 50% of being in the positive class.

It has a probability of 0% of being in the positive class.

It has a probability of 50% of being in the negative class.

Check all that apply. If a given data point has a logit value equals zero:

Check all that apply. If a given data point has a logit value equals zero:

The binary cross-entropy loss is given by averaging the logarithm of the predicted probability of each point being in the:

The binary cross-entropy loss is given by averaging the logarithm of the predicted probability of each point being in the:

The more dimensions, the ____ separable the data points are.

The more dimensions, the ____ separable the data points are.

The model `nn.Sequential(nn.Linear(2, 1))` is used in a binary classification task. Which loss function should be used with it?

The model <code>nn.Sequential(nn.Linear(2, 1))</code> is used in a binary classification task. Which loss function should be used with it?

Is the code snippet below correct?

```python
loss_fn = nn.BCELoss(reduction='mean')
loss = loss_fn(labels, predicted_probabilities)
```

Is the code snippet below correct?
<pre><code class="language-python">loss_fn = nn.BCELoss(reduction='mean')
loss = loss_fn(labels, predicted_probabilities)
</code></pre>

The “accuracy” is always going to be a good metric to evaluate a classification model.

The “accuracy” is always going to be a good metric to evaluate a classification model.

What is the shape of the decision boundary of logistic regression with two features?

What is the shape of the decision boundary of logistic regression with two features?

Check all that apply. There is a trade-off between these two metrics:

Check all that apply. There is a trade-off between these two metrics:

The model `nn.Sequential(nn.Linear(2, 1), nn.Sigmoid())` is used in a binary classification task. Which loss function should be used with it?

The model <code>nn.Sequential(nn.Linear(2, 1), nn.Sigmoid())</code> is used in a binary classification task. Which loss function should be used with it?

The values in a confusion matrix depend on the probability threshold used to classify the data points:

The values in a confusion matrix depend on the probability threshold used to classify the data points:

Test your understanding of the concepts explained in this chapter with this quiz!

Introduction

Visualizing Gradient Descent

A Simple Regression Problem

Rethinking the Training Loop

Going Classy

A Simple Classification Problem

Appendix

Conclusion

Quiz