Paper Review: Sequence to Sequence Learning with Neural Networks

preview_player
Показать описание
In this video I read through and do a paper summary of one of the first Seq2Seq papers, specifically "Sequence to Sequence Learning with Neural Networks" and in the next video we will implement this paper, or at least a variant of it!

Paper:

❤️ Support the channel ❤️

Paid Courses I recommend for learning (affiliate links, no extra cost for you):

✨ Free Resources that are great:

💻 My Deep Learning Setup and Recording Setup:

GitHub Repository:

✅ One-Time Donations:

▶️ You Can Connect with me on:
  1. Aladdin Persson
  2. Sequence to Sequence paper
  3. deeplearning paper
  4. nlp translation paper
Рекомендации по теме
Paper Review: Sequence 0:11:30

Paper Review: Sequence to Sequence Learning with Neural Networks

Sequence-to-Sequence (seq2seq) Encoder-Decoder 0:16:50

Sequence-to-Sequence (seq2seq) Encoder-Decoder Neural Networks, Clearly Explained!!!

[Paper Review] Sequence 0:20:49

[Paper Review] Sequence to Sequence Learning with Neural Network

Convolutional Sequence to 0:06:00

Convolutional Sequence to Sequence Learning Detailed Explanation

[Paper Review] Dcoument 0:18:19

[Paper Review] Dcoument Ranking with a Pretrained Sequence to Sequence Model

Sequence-to-Sequence Learning with 0:04:58

Sequence-to-Sequence Learning with Neural Networks

Sequence to Sequence 0:57:21

Sequence to Sequence Learning with Neural Networks

Recent Advances in 0:06:39

Recent Advances in Deep Learning Methods in Materials

Convolutional Sequence to 0:15:46

Convolutional Sequence to Sequence Learning | Lecture 55 (Part 2) | Applied Deep Learning

Sequence-to-Sequence Models w/ 0:03:53

Sequence-to-Sequence Models w/ Conversational Structure for Abstractive Dialogue Summarization

BART: Denoising Sequence-to-Sequence 0:12:47

BART: Denoising Sequence-to-Sequence Pre-training for NLG (Research Paper Walkthrough)

CS 182: Lecture 0:21:55

CS 182: Lecture 11: Part 1: Sequence to Sequence

Pytorch Seq2Seq Tutorial 0:50:55

Pytorch Seq2Seq Tutorial for Machine Translation

CMU Multilingual NLP 0:43:51

CMU Multilingual NLP 2020 (7): Machine Translation/Sequence-to-sequence Models

We Don’t Sequence 0:09:00

We Don’t Sequence Whole Genomes Much - Here’s Why | Paper Review

Paper review 0003: 0:19:19

Paper review 0003: Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

[Paper Review] Learning 0:24:39

[Paper Review] Learning Phrase Representations using RNN Encoder-Decoder

Sequence Analysis for 0:59:57

Sequence Analysis for Social Science (Feb. 2022) Part 3

[Paper Review] Multimodal 0:31:21

[Paper Review] Multimodal Transformer for Unaligned Multimodal Language Sequences

CMU Neural Nets 0:27:23

CMU Neural Nets for NLP 2021 (15): Sequence-to-sequence Pre-training

Sequence Models Complete 5:55:34

Sequence Models Complete Course

The Human Genome 0:09:45

The Human Genome Project - What Did We Learn? | Paper Review

Sequence to Sequence 0:12:57

Sequence to Sequence Learning | Lecture 52 (Part 2) | Applied Deep Learning

Abstractive Text Summarization 1:00:38

Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond | TDLS

Комментарии
Автор

This was my first time going through a paper in my videos. I learned a lot of things and have some ideas for how I can improve them for future paper review videos. Would love feedback on it as well :)

AladdinPersson
Автор

It would be helpful if you could specifically point out which input/output/token you're talking about when you refer to the graph - for example, when you say "start token", put your cursor/circle the <sos> in the picture, and explain what the yellow and green and blue squares represent (and even more, use an example to mimic the flow of the model).It's a lot more helpful to walk through one example using the picture than speaking to it more abstractly. and maybe less "you know" would sound more smooth! thanks for the video :)

krystaljinluma