LSTM Networks: Explained Step by Step!

Показать описание

Why we need LSTM networks, how they work step by step, and full explanations: visual and mathematical!

0:00 Problem with Simple RNNs
11:45 Goal of LSTM
12:55 Introducing the Cell State
14:27 Step 1: The Candidate Cell State
15:52 Step 2: The Forget Gate
17:48 Step 3: The Input Gate
18:18 Step 4: The New Cell State
21:15 Step 5: The Output Gate
22:31 Step 6: The New Output State
22:57 Visual Diagram
27:14 Recap all Variables
29:49 Why does this work?

---

---

Icon References:

Dog icons created by Freepik - Flaticon

Gate icons created by Freepik - Flaticon

Memory icons created by Freepik - Flaticon

Crystal ball icons created by Freepik - Flaticon

Khao manee cat icons created by Pixel perfect - Flaticon

Рекомендации по теме

Комментарии

At first I was inclined to click away from the video because of the unorthodox explanation of LSTM in "steps", which was different to what I had seen in other videos and blog posts which focus on the infamous LSTM diagram. However, I was struggling to fully grasp LSTMs so I decided to give the video a try. And it paid off! I can't believe LSTMs are that simple! This video is absolutely essential for understanding LSTMs at a fundamental level.

rajpulapakura

the great thing about your videos is that I am always guaranteed to learn something and learn it with much better understanding.

wryltxw

i have listened to a 2-hour lecture in my MSc data science, still don't know what is happening. Your video is explain it in a succinct way!!! Thank you!!!

LifeKiT-i

Your videos (specifically sampling and deep learning videos) helped me a lot during my master's. Thanks for all the videos!

juaneshberger

Best explanation of LSTMs on the internet

vzinko

Thank you so much for your videos! They are super informative and much more intuitive than the hundreds of slides I have from my master's class. Keep up the great work!

thankgoodnessitstheweekend

Extremely good and helpful! A great genuine desire to help learners by explaining difficult ideas in a most self effacing manner! Many thanks!

charleskangai

I've been trying to understand LSTM through multiple blogs and videos but the thing that why it needs to be this complex, you specifically targeted that point of view to understand it, this is really one of the best videos, because you showed why there was a need for a LSTM and how could the gaps be filled, which is what made it very easy to understand . Could you please list the references as well for the video, so that if anyone has to go further deep into the concepts, it would be very helpful ! Thanks a lot for this video !

karanmaniyar

Plz continue the same good work by blending Mathematics with simple Real time example. Fantastic Explanation👍

chaitrab

This is an extremely good explanation. Thanks for all the effort and sharing!!

pushkarparanjpe

Thanks for the video!! Just what I needed for my ML midterm exam. Will be waiting for the Transformers topic that I believe build upon this concept.

carlosenriquehuapayaavalos

super helpful. I cant thank you enough for making this explanation

rizkabritania

So happy you did this video!!! :D Thank you for all the great work!

golnoushghiasi

I love your videos, keep up the awesome work!!!

santiagolicea

Just amazing intuition! Thanks so much for the great content.

billdepo

Great video as always!

The part that still perplexes me:
How does the LSTM "know" what is important (like dog) and when to actually use that to predict the next word?

KarthikNaga

A video about transformers and GANs in this style would be awesome as well.

juaneshberger

Hi Ritvik,

It will be really great if you could create videos which explain maths behind ML models like SVM and PCA.I am also curious about ODE, PDE, real analysis, complex analysi and stochastic calculus. But the problem is that i want to explore topics which are relevant to financial engineering. So i could read all quant finance related textbooks. I am a professional and really dont have time to read all applied maths textbooks 😅.

_Sam_-zhsw

Hi Ritvik. It would be amazing if you could better organize the playlists.(chronological and right videos in right playlists)

teetanrobotics

Thank you very much! I have a few questions:

1. Could you please explain the reasoning behind using a candidate cell state and why the tanh activation function is necessary?

2. I have noticed that many implementations, papers, or blogs I have read use concatenation of h[t-1] and x[t] and a single learnable weight matrix W instead of U and V used in this video. Can you clarify why this is the case?

3. Despite the success of the model in predicting words, I remain somewhat skeptical about how it achieves such accuracy. :)

prateekcaire

LSTM Networks: Explained Step by Step!

LSTM Networks: Explained Step by Step!

What is LSTM (Long Short Term Memory)?

Long Short-Term Memory (LSTM), Clearly Explained

Illustrated Guide to LSTM's and GRU's: A step by step explanation

Deep Learning: Long Short-Term Memory Networks (LSTMs)

LSTM Networks - EXPLAINED!

LSTM Networks Explained for Beginners

Simple Explanation of LSTM | Deep Learning Tutorial 36 (Tensorflow, Keras & Python)

Human and AI Interaction | 2.4 - Introduction to Neural Networks | Purdue University

How LSTM Networks Work? | Deep Learning | Simple Explanation

Neural Networks Explained in 5 minutes

Recurrent Neural Networks (RNNs), Clearly Explained!!!

18- Long Short Term Memory (LSTM) Networks Explained Easily

Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM)

Tutorial 34- LSTM Recurrent Neural Network In Depth Intuition

Understanding LSTM Networks

Long Short Term Memory (LSTM) Networks in 20 minutes

Recurrent Neural Networks (RNNs and LSTMs) explained in detail !

What are LSTMs?

Introduction to Long Short-Term Memory Networks | What Is LSTM | Edureka | DL Live -1

What are Convolutional Neural Networks (CNNs)?

165 - An introduction to RNN and LSTM

But what is a neural network? | Deep learning chapter 1

Illustrated Guide to Recurrent Neural Networks: Understanding the Intuition