From the course: Deep Learning Fundamentals for Healthcare

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Building and implementing neural networks: TensorFlow

Building and implementing neural networks: TensorFlow

From the course: Deep Learning Fundamentals for Healthcare

Start my 1-month free trial Buy for my team

Building and implementing neural networks: TensorFlow

“

- [Instructor] In the previous chapters, we explored neural networks, their theory, and their core components. Now, let's move on to building and implementing neural networks in practice. We'll be writing and running the code using Google Colab notebooks. To get started, go to colab.google.com. If you're logged into your Google account, you should see an interface like this. If you're not, you will be prompted to log in. Our sample task will be to build a basic binary classification model that can predict whether a sample belongs to a class zero or class one. We will be implementing this task using both TensorFlow and PyTorch, allowing us to compare their structure and ease of use. In the upper part of the notebook, select Runtime. Change runtime, and choose GPU as the hardware accelerator. GPU enables significantly faster training speed by offloading computationally-intensive task from the CPU to the GPU. This is especially beneficial for deep learning models, which often involve…

Contents