Welcome back to Machine Learning Guide. I'm your host, Tyler Rinelli.

MLG teaches the fundamentals of machine learning and artificial intelligence.

It covers intuition, models, math, languages, frameworks, and more.

Where your other machine learning resources provide the trees, I provide the forest.

Visual is the best primary learning modality, but audio is a great supplement during exercise commute and chores.

Consider MLG your syllabus with highly curated resources for each episode's details at OCdevel.com forward slash MLG.

I'm also starting a new podcast which could use your support.

It's called Lefnear's Life Hacks and teaches productivity focused tips and tricks,

some which could prove beneficial in your machine learning education journey.

Find that at Ocdevel.com forward slash LLH.

This is episode 23, Deep NLP Part 2.

In this episode, I will finally wrap up on NLP.

This is the second episode of Deep NLP, RNNs.

And we're going to cover a few fine points about RNNs.

We'll talk about bidirectional RNNs, the vanishing and exploding gradient problem

of back propagation and its solution through LSTMs or GRUs. But let's start with a review of

RNNs because I think that last episode went a little bit fast and so I want to make sure that you

understand RNNs completely

before we move on. So in deep learning, we use neural networks, and there are various flavors of

neural networks for different tasks. The vanilla neural network, also called a multi-layer perceptron

or a feed-forward network, or usually just a neural network.

Is used for sort of general tasks, general classification or regression problems.

...