Deep Learning

You might have started to notice a pattern in our Python code examples when training neural networks. There are four main ingredients you need to put together in your own neural network and deep learning algorithm: a dataset, a model/architecture,…

In this tutorial, we will discuss the concept of weight initialization, or more simply, how we initialize our weight matrices and bias vectors. This tutorial is not meant to be a comprehensive initialization technique; however, it does highlight popular methods,…

In this tutorial, you will learn: What gradient descent is How gradient descent enables us to train neural networks Variations of gradient descent, including Stochastic Gradient Descent (SGD) How SGD can be improved using momentum and Nesterov acceleration To learn…

Deep learning methods are representation-learning methods with multiple levels of representation, obtained by composing simple but nonlinear modules that each transform the representation at one level (starting with the raw input) into a representation at a higher, slightly more abstract…

Based on our previous two sections on image classification and types of learning algorithms, you might be starting to feel a bit steamrolled with new terms, considerations, and what looks to be an insurmountable amount of variation in building an…

Recently, we’ve spent a reasonable amount of time discussing image fundamentals, types of learning, and even a four-step pipeline we can follow when building our own image classifiers. But we have yet to build an actual image classifier of our…

In this blog post, I interview Gary Song, a deep learning practitioner at Unity Technologies. We’re now at the one-year anniversary of COVID-19. It’s been a particularly rough year for all of us. For Gary, it was really bad. But…

In this tutorial, you will learn how to generate image batches of (1) normal images and (2) adversarial images during the training process. Doing so improves your model’s ability to generalize and defend against adversarial attacks. Last week we learned…

In this tutorial, you will learn how to defend against adversarial image attacks using Keras and TensorFlow. So far, you have learned how to generate adversarial images using three different methods: Adversarial images and attacks with Keras and TensorFlow Targeted…