Showing posts with label LSTM. Show all posts

Saturday, April 8, 2023

Part G: Text Classification with a Recurrent Layer

Keras environment.
We will use a Kaggle Dataset in which there are 32 topics and more than 400K total reviews.
If you would like to learn more about Deep Learning with practical coding examples,
Please subscribe to the Murat Karakaya Akademi YouTube Channel or
Follow my blog on muratkarakaya.net
Do not forget to turn on notifications so that you will be notified when new parts are uploaded.
You can access all the codes, videos, and posts of this tutorial series from the links below.
Accessible on:
YouTube in English
YouTube in Turkish
muratkarakaya.net
Github pages
Github Repo
Google Colab

PARTS
In this tutorial series, there are several parts to cover Text Classification with various Deep Learning Models topics. You can access all the parts from this index page.

In this part, we will use the Keras Bidirectional LSTM layer in a Feed Forward Network (FFN).

If you are not familiar with the Keras LSTM layer or the Recurrent Networks concept, you can check in the following Murat Karakaya Akademi YouTube playlists:

English:

All About LSTM

Turkish

LSTM hakkında herşey!

If you are not familiar with the classification with Deep Learning topic, you can find the 5-part tutorials in the below Murat Karakaya Akademi YouTube playlists:

Photo by Markus Spiske on Unsplash

Seq2Seq Learning Part B: Using the LSTM layer in a Recurrent Neural Network

SEQ2SEQ LEARNING Part B: Using the LSTM layer in a Recurrent Neural Network

Welcome to the Part B of the Seq2Seq Learning Tutorial Series. In this tutorial, we will use several Recurrent Neural Network models to solve the sample Seq2Seq problem introduced in Part A.

We will use LSTM as the Recurrent Neural Network layer in Keras.

You can access all my SEQ2SEQ Learning videos on Murat Karakaya Akademi Youtube channel in ENGLISH or in TURKISH

You can access all the tutorials in this series from my blog at www.muratkarakaya.net

If you would like to follow up on Deep Learning tutorials, please subscribe to my YouTube Channel or follow my blog on muratkarakaya.net. Thank you!

Photo by Jess Bailey on Unsplash

Seq2Seq Learning Part C: Basic Encoder-Decoder Architecture & Design

Welcome to the Part C of the Seq2Seq Learning Tutorial Series. In this tutorial, we will design a Basic Encoder-Decoder model to solve the sample Seq2Seq problem introduced in Part A.

We will use LSTM as the Recurrent Neural Network layer in Keras.

You can access all my SEQ2SEQ Learning videos on Murat Karakaya Akademi Youtube channel in ENGLISH or in TURKISH

You can access all the tutorials in this series from my blog at www.muratkarakaya.net

If you would like to follow up on Deep Learning tutorials, please subscribe to my YouTube Channel or follow my blog on muratkarakaya.net. Thank you!

Photo by Med Badr Chemmaoui on Unsplash

LSTM: Understanding Output Types

INTRODUCTION

In this tutorial, we will focus on the outputs of the LSTM layer in Keras. To create powerful models, especially for solving Seq2Seq learning problems, LSTM is the key layer. To use LSTM effectively in models, we need to understand how it generates different results with respect to given parameters. Therefore, in this tutorial, we will learn and use 3 important parameters (units, return_sequences, and return_state).

At the end of the tutorial, you will be able to manage the LSTM layer to satisfy the model requirements correctly.

If you would like to follow up on Deep Learning tutorials, please subscribe to my YouTube Channel or follow my blog on muratkarakaya.net. Thank you!

Photo by Victor Barrios on Unsplash

LSTM: Understanding the Number of Parameters

In this tutorial, we will focus on the internal structure of the Keras LSTM layer in order to understand how many learnable parameters an LTSM layer has.

Why do we need to care about calculating the number of parameters in the LSTM layer since we can easily get this number in the model summary report?

Well, there are several reasons:

First of all, to calculate the number of learnable parameters correctly, we need to understand how LSTM is structured and how LSTM operates in depth. Thus, we will delve into LSTM gates and gate functions. We will gain precious insight into how LSTM handles time-dependent or sequence input data.
Secondly, in ANN models, a number of parameters is a really important metric for understanding the model capacity and complexity. We need to keep an eye on the number of parameters of each layer in the model to handle overfitting or underfitting situations. One way to prevent these situations is to adjust the number of parameters of each layer. We need to know how the number of parameters actually affects the performance of each layer.

If you want to enhance your understanding of the LSTM layer and learn how many learnable parameters it has please continue this tutorial.

By the way, I would like to mention that in my Youtube channel I have a dedicated playlist in English (All About LSTM) and in Turkish (LSTM Hakkında Herşey). You can check these playlists to learn more about LSTM.

Lastly, if you want to be notified of upcoming tutorials about LSTM and Deep Learning please subscribe to my Youtube channel and activate notifications.

Thank you!

Now, let’s get started!

Photo by Sigmund on Unsplash

SEQ2SEQ LEARNING PART D: Encoder-Decoder with Teacher Forcing

Welcome to Part D of the Seq2Seq Learning Tutorial Series. In this tutorial, we will design an Encoder-Decoder model to be trained with “Teacher Forcing” to solve the sample Seq2Seq problem introduced in Part A.

We will use the LSTM layer in Keras as the Recurrent Neural Network.

You can access all my SEQ2SEQ Learning videos on Murat Karakaya Akademi Youtube channel in ENGLISH or in TURKISH

You can access all the tutorials in this series from my blog at www.muratkarakaya.net. If you would like to follow up on Deep Learning tutorials, please subscribe to my YouTube Channel or follow my blog on muratkarakaya.net. You can also access this Colab Notebook using the link.

If you are ready, let’s get started!

Photo by Vedrana Filipović on Unsplash

SEQ2SEQ LEARNING PART E: Encoder-Decoder for Variable Input And Output Sizes: Padding & Masking

Welcome to Part E of the Seq2Seq Learning Tutorial Series. In this tutorial, we will design an Encoder-Decoder model to handle variable-size input and output sequences by using Padding and Masking methods. We will train the model by using the Teacher Forcing technique which we covered in Part D.

You can access all my SEQ2SEQ Learning videos on Murat Karakaya Akademi Youtube channel in ENGLISH or in TURKISH. You can access all the tutorials in this series from my blog at www.muratkarakaya.net. You can access this Colab Notebook using the link.

If you would like to follow up on Deep Learning tutorials, please subscribe to my YouTube Channel or follow my blog on muratkarakaya.net.

If you are ready, let’s get started!

Photo by Jeffrey Brandjes on Unsplash

Sequence To Sequence Learning With Tensorflow & Keras Tutorial Series

This is the Index page of the “SEQ2SEQ Learning in Deep Learning with TensorFlow & Keras” tutorial series.

You can access all the content of the series in English and Turkish as YouTube videos, Medium posts, and Collab / GitHub Jupyter Notebooks using the below links..

Last Updated: 27 May 2021

Encoder-Decoder Model with Global Attention

Saturday, April 8, 2023