In this tutorial we go through how an image captioning system works and implement one from scratch. Specifically we're looking at the caption dataset Flickr8k. There are multiple ways to improve the model: train a larger model (the one used is relatively small), train for longer and improve the model by adding attention similar to this paper: https://arxiv.org/abs/1502.03044.

Video of dataset (link in that video description to download the dataset yourself):
https://youtu.be/9sHcLvVXsns

✅ Support My Channel Through Patreon:
https://www.patreon.com/aladdinpersson

PyTorch Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf

Github Repository:
https://github.com/aladdinpers....son/Machine-Learning

I stole the thumbnail image from Yunjeys Github on Image Captioning which I also used as a resource. The implementation in the video differs a bit, but it's definitely worth checking out:
https://github.com/yunjey/pytorch-tutorial


OUTLINE:
0:00 - Introduction
0:12 - Explanation of Image Captioning
05:15 - Overview of the code
06:07 - Implementation of CNN and RNN
20:03 - Setting up the training
30:36 - Fixing errors
32:18 - Small evaluation and ending

A from scratch implementation of SVM using the CVXOPT package in Python to solve the quadratic programming. Specifically implementation of soft margin SVM.

To understand the theory (which is a bit challenging) I recommend reading the following:
* http://cs229.stanford.edu/notes/cs229-notes3.pdf

* https://www.youtube.com/playli....st?list=PLoROMvodv4r (Lectures 6,7 by Andrew Ng)


People often ask what courses are great for getting into ML/DL and the two I started with is ML and DL specialization both by Andrew Ng. Below you'll find both affiliate and non-affiliate links if you want to check it out. The pricing for you is the same but a small commission goes back to the channel if you buy it through the affiliate link.
ML Course (affiliate): https://bit.ly/3qq20Sx
DL Specialization (affiliate): https://bit.ly/30npNrw
ML Course (no affiliate): https://bit.ly/3t8JqA9
DL Specialization (no affiliate): https://bit.ly/3t8JqA9

GitHub Repository:
https://github.com/aladdinpers....son/Machine-Learning

✅ Equipment I use and recommend:
https://www.amazon.com/shop/aladdinpersson

❤️ Become a Channel Member:
https://www.youtube.com/channe....l/UCkzW5JSFwvKRjXABI

✅ One-Time Donations:
Paypal: https://bit.ly/3buoRYH
Ethereum: 0xc84008f43d2E0bC01d925CC35915CdE92c2e99dc

▶️ You Can Connect with me on:
Twitter - https://twitter.com/aladdinpersson
LinkedIn - https://www.linkedin.com/in/al....addin-persson-a95384
GitHub - https://github.com/aladdinpersson

PyTorch Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf

This week we’re looking into transformers. Transformers were introduced a couple of years ago with the paper Attention is All You Need by Google Researchers. Since its introduction transformers has been widely adopted in the industry.

Get your Free Token for AssemblyAI Speech-To-Text API 👇
https://www.assemblyai.com/?utm_source=youtube&utm_medium=referral&utm_campaign=yt_mis_8&utm_id=yt_mis_8

Models like BERT, GPT-3 made groundbreaking improvements in the world of NLP using transformers. Since then model libraries like hugging face made it possible for everyone to use transformer based models in their projects. But what are transformers and how do they work? How are they different from other deep learning models like RNNs, LSTMs? Why are they better?

In this video, we learn about it all!

Some of my favorite resources on Transformers:
The original paper - https://arxiv.org/pdf/1706.03762.pdf
If you’re interested in following the original paper with the code - http://nlp.seas.harvard.edu/20....18/04/03/attention.h
The Illustrated Transformer – https://jalammar.github.io/ill....ustrated-transformer
Blog about positional encodings - https://kazemnejad.com/blog/tr....ansformer_architectu
About attention - Visualizing A Neural Machine Translation Model - https://jalammar.github.io/vis....ualizing-neural-mach
Layer normalization - https://arxiv.org/abs/1607.06450


Some images used in this video are from:
https://colah.github.io/posts/....2015-08-Understandin
https://jalammar.github.io/vis....ualizing-neural-mach
https://medium.com/nanonets/ho....w-to-easily-build-a-
https://medium.com/swlh/elegan....t-intuitions-behind-