Latest videos
#PaperExplained #PaperReview
Paper: https://arxiv.org/abs/1810.04805
Useful resources to learn about transformers:
https://peterbloem.nl/blog/transformers
https://nlp.seas.harvard.edu/2....018/04/03/attention.
https://jalammar.github.io/ill....ustrated-transformer
Useful resources to learn about BERT:
https://jalammar.github.io/illustrated-bert/
In this video we will cover how to build a neural network in TensorFlow 2.0 using the Keras Sequential and Functional API. We also take a look at other details like how we obtain the output features from specific layers and obtaining summaries of the model etc.
Resources or prerequisite videos:
1. 3Blue1Brown:
https://www.youtube.com/playli....st?list=PLZHQObOWTQD
2. Deep Learning Specialization Course 1 (Probably don't need to watch all):
https://www.youtube.com/playli....st?list=PLkDaE6sCZn6
2. Deep Learning Specialization Course 2 (Probably don't need to watch all):
https://www.youtube.com/playli....st?list=PLkDaE6sCZn6
I learned a lot and was inspired to make these TensorFlow videos by the TensorFlow Specialization on Coursera. Below you'll find both affiliate and non-affiliate links, the pricing for you is the same but a small commission goes back to the channel if you buy it through the affiliate link.
affiliate: https://bit.ly/3t3tgI5
non-affiliate: https://bit.ly/3kZgN5B
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
TensorFlow Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf
OUTLINE:
0:00 - Introduction
0:40 - Resources for theory
1:06 - Imports
3:13 - Loading Mnist dataset
5:56 - Using Sequential API
14:10 - Using Functional API
17:20 - Extracting specific layer features
19:53 - Suggestions to try out
Full title: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Paper: https://arxiv.org/abs/1905.11946
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
The video focuses how to get started but particularly on the prompt engineering part to give you ideas and inspiration to what you can explore. Since Stable Diffusion was released couple of days ago this has been incorporated into MidJourney too which you can access by "—beta" argument which supposedly helps with face quality.
Resources mentioned:
https://github.com/willwulfken..../MidJourney-Styles-a
https://pitch.com/v/DALL-E-prompt-book-v1-tmd33y
https://docs.google.com/docume....nt/d/11WlzjBT0xRpQhP
Timestamps:
0:00 - Introduction to MJ and what you can do
8:17 - Resources for prompt inspiration
12:30 - How to iterate on the prompt/caption (prompt engineering)
29:40 - Other arguments you can use
32:26 - Final images result
33:25 - Ending
In many scenarios you need to create more custom training than what model.fit supports and what's great is that we can actually modify how a training step is done inside model.fit and increase the flexibility of training models. In this video I show how this can be done and add more flexibility, then in the next video I will show you how to build custom training loops completely from scratch for scenarios where even more flexibility is needed.
I learned a lot and was inspired to make these TensorFlow videos by the TensorFlow Specialization on Coursera. Below you'll find both affiliate and non-affiliate links, the pricing for you is the same but a small commission goes back to the channel if you buy it through the affiliate link.
affiliate: https://bit.ly/3t3tgI5
non-affiliate: https://bit.ly/3kZgN5B
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
TensorFlow Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf
In this video we explore a more real example of using the Functional API to classify multi digit MNIST. So far all we the examples have been simple use cases where you actually can use the Sequential API and it would work, but here we see a real limitation and where we would have to use the Functional API. In the next video we will see how to build even more flexible models using Subclassing.
Code:
https://github.com/AladdinPerz....on/Machine-Learning-
Dataset:
https://www.kaggle.com/dataset..../eb9594e5b728b2eb74f
I learned a lot and was inspired to make these TensorFlow videos by the TensorFlow Specialization on Coursera. Below you'll find both affiliate and non-affiliate links, the pricing for you is the same but a small commission goes back to the channel if you buy it through the affiliate link.
affiliate: https://bit.ly/3t3tgI5
non-affiliate: https://bit.ly/3kZgN5B
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
TensorFlow Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf
This is my solution to oneVsAll.m function in Programming assignment 3 from the famous Machine Learning course by Andrew Ng.
Github: https://github.com/AladdinPerz....on/Courses/tree/mast
I was inspired to make these videos by this specialization: https://bit.ly/3SqLuA6
In this video we build a generative adversarial network based on convolutional neural networks and train it on the CelebA dataset. This is a huge improvement from the previous simple fully connected GAN implemented in previous videos.
DCGAN paper:
https://arxiv.org/abs/1511.06434
CelebA dataset used in video:
https://www.kaggle.com/dataset..../504743cb487a5aed565
GitHub Repository:
https://github.com/aladdinpers....son/Machine-Learning
GAN Playlist:
https://youtube.com/playlist?l....ist=PLhhyoLH6IjfwIp8
PyTorch Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf
OUTLINE:
0:00 - Introduction
0:26 - Quick Paper Recap
4:31 - Implementation of Discriminator
9:38 - Implementation of Generator
15:27 - Weight initialization and test model
19:09 - Setup of training
31:36 - Training on MNIST
32:20 - Modifications to CelebA dataset
33:52 - Training on CelebA and ending
Full title: RandAugment: Practical automated data augmentation with a reduced search space
Paper link: https://arxiv.org/abs/1909.13719
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
AI For Medicine Specialization: https://bit.ly/3yAPYgh
My review and thoughts of my experience doing this specialization by deeplearning.ai on Coursera. Let me know if you have any questions or if you have taken it please do share your thoughts as it could be useful for others considering it :)
Timestamps:
0:00 - Introduction
01:29 - Course Contents
11:25 - Prerequisites & thoughts
13:45 - Course Structure
18:45 - Few Details
20:57 - Summary & Rating
In this video we go through how to perform data augmentation on your dataset and show two ways of doing it. The primary method is by first having a TF Dataset and applying a map augment function that is applied to each image. The second method (on newer versions of TF 2.3.0) you can make it part of your model.
Links mentioned for docs mentioned in video:
https://www.tensorflow.org/api...._docs/python/tf/imag
https://www.tensorflow.org/api...._docs/python/tf/kera
I learned a lot and was inspired to make these TensorFlow videos by the TensorFlow Specialization on Coursera. Below you'll find both affiliate and non-affiliate links, the pricing for you is the same but a small commission goes back to the channel if you buy it through the affiliate link.
affiliate: https://bit.ly/3t3tgI5
non-affiliate: https://bit.ly/3kZgN5B
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
TensorFlow Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf
I was inspired to make these videos by this specialization: https://bit.ly/3SqLuA6
Progressive Growing of GANs for Improved Quality, Stability, and Variation: https://arxiv.org/abs/1710.10196
#PaperReview #PaperExplained
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
GAN Playlist:
https://youtube.com/playlist?l....ist=PLhhyoLH6IjfwIp8
PyTorch Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf
Timestamps:
0:00 - Introduction
0:34 - Overview
5:06 - Progressive growing
7:36 - MiniBatch Std
9:15 - Fading in new layers
13:37 - Normalization (PixelNorm & Eq. LR)
20:30 - Some results
20:55 - Implementations details
30:59 - Ending
I was inspired to make these videos by this specialization: https://bit.ly/3SqLuA6
In this video we take a look at a way of also deciding what the output from the GAN should be. Specifically the output is conditioned on the labels that we send in and as an example we take a look at training on MNIST (of course) ;) But these ideas extend to any dataset you're working with really!
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
▶️ 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
GAN Playlist:
https://youtube.com/playlist?l....ist=PLhhyoLH6IjfwIp8
PyTorch Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf
OUTLINE:
0:00 - Introduction
0:56 - Modifying Generator and Discriminator
6:58 - Modifying Gradient Penalty
7:35 - Modifying Training
10:43 - Evaluation & Ending
In this video we code the K-means clustering algorithm from scratch in the Python programming language. Below I link a few resources to learn more about K means clustering as well as to the Machine Learning Github repository where you can also find the code!
Resources to learn more about K means:
https://youtu.be/Ev8YbxPu_bQ (Watch the following lectures 13.2, 13.3, 13.4, 13.5 also)
http://cs229.stanford.edu/notes/cs229-notes7a.pdf
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
In this video I show you how to get even more flexibility during training and that is by creating the training loops from scratch. In many ways it's similar to customizing model.fit but here we are removing the model.fit API entirely.
I learned a lot and was inspired to make these TensorFlow videos by the TensorFlow Specialization on Coursera. Below you'll find both affiliate and non-affiliate links, the pricing for you is the same but a small commission goes back to the channel if you buy it through the affiliate link.
affiliate: https://bit.ly/3t3tgI5
non-affiliate: https://bit.ly/3kZgN5B
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
TensorFlow Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf
Watch my previous video on the paper walkthrough to understand the theory behind VAEs. Hopefully you find the video useful to understand VAEs in depth! :)
Useful article on VAEs:
https://sannaperzon.medium.com..../paper-summary-varia
Timestamps:
0:00 - Introduction
2:45 - Model architecture
15:50 - Training loop
31:10 - Inference example
39:10 - Ending
