From the course: Natural Language Processing in Python

Unlock this course with a free trial

Join today to access over 26,400 courses taught by industry experts.

Solution: Deep learning concepts

Solution: Deep learning concepts - Python Tutorial

From the course: Natural Language Processing in Python

Start my 1-month free trial Buy for my team

Solution: Deep learning concepts

“

Let's start with the terms on the left here. The first thing we're looking at is something that has one to two hidden layers and that is a neural network. And then a model that has three or more hidden layers is called deep learning. So that's really the difference between neural networks and deep learning. Next we're looking for a building block for other architectures and that's a feed forward neural network. It's the most basic deep learning architecture but it's usually used inside of other architectures. We're also looking for an architecture that's used for image-related tasks and that is convolutional neural networks. And then here we have an architecture that's used for NLP tasks but it's an outdated one and those are RNNs and LSTMs. Those are for sequential data but they have been replaced by transformers. And that's this next one here. This architecture is used for NLP tasks, and those are transformers. And for these final two down here, we have a mindset where you train…

Contents