Skip to content

Add new ML/DL resources for issue #445 #446

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add new ML/DL resources for issue #445 #446

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
306 changes: 112 additions & 194 deletions ML/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,19 +1,19 @@
> Use this format to add your own ML resources (those that were personally used by you) in this README
```
<!--
> Use this format to add your own ML resources (those that were personally used by you) in this README

```
## YOUR_NAME
<a href="YOUR_LINKEDIN_PROFILE_LINK">
<a href="YOUR_LINKEDIN_LINK">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>

[![Generic badge](https://img.shields.io/badge/Year-YOUR_YEAR-<COLOR>.svg)](https://shields.io/)
[![Generic badge](https://img.shields.io/badge/Year-YOUR_YEAR-<color>.svg)](https://shields.io/)
```
YOUR_ANSWER

```
```
<br />

# Machine Learning

```
-->
# Machine Learning
![forthebadge](https://img.shields.io/badge/Python-FFD43B?style=for-the-badge&logo=python&logoColor=darkgreen)
![forthebadge](https://img.shields.io/badge/scikit_learn-F7931E?style=for-the-badge&logo=scikit-learn&logoColor=white)
![forthebadge](https://img.shields.io/badge/Jupyter-F37626.svg?&style=for-the-badge&logo=Jupyter&logoColor=white)
Expand All @@ -26,8 +26,7 @@
<a href="https://www.linkedin.com/in/aditya-rana-swe/">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>

[![Generic badge](https://img.shields.io/badge/Batch-2023-<COLOR>.svg)](https://shields.io/)
[![Generic badge](https://img.shields.io/badge/Batch-2023-<color>.svg)](https://shields.io/)
```
1. Basics - python
Sololearn app/website - https://www.sololearn.com/learning/1073
Expand All @@ -39,241 +38,116 @@ Applied data science - https://www.coursera.org/specializations/data-science-pyt

3. Journey
Learnt python in school from several different resources and got started with deep learning specialization towards the end of 1st year.

4. Blogs
Medium - https://medium.com/
Towardsdatascience - https://towardsdatascience.com/
```
## Vibhu Chandransh Bhanot
<a href="https://www.linkedin.com/in/vibhu-chandransh-bhanot-624720192">

## Mani Bansal
<a href="https://www.linkedin.com/in/mani-bansal/">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>
[![Generic badge](https://img.shields.io/badge/Batch-2022-<color>.svg)](https://shields.io/)
```
Great Resources for learning AI and ML :

[![Generic badge](https://img.shields.io/badge/Batch-2023-<COLOR>.svg)](https://shields.io/)
![Generic badge](https://img.shields.io/badge/R%26D-member-blue)
1) Free Quality courses to get started with :

```
Exploratory data analysis
There are a lot of online tutorials out there but I used the following which worked pretty well for me:
1) Python Data Science Handbook by Jake VanderPlas
Chapters: 2,3 in detail and initial part of ch 4….(to start with numpy, pandas and matplotlib)
https://tanthiamhuat.files.wordpress.com/2018/04/pythondatasciencehandbook.pdf
2) Introduction to data science with python coursera (University of Michigan)...(used to practise pandas)
https://www.coursera.org/learn/python-data-analysis

Machine Learning Algorithms
Used parallel combination of Hands-On ML with scikit-learn,keras & TF (for checking out implementation and basic theory) and Andrew Ng stanford coursera course (for deeper parts of theory)
https://www.coursera.org/learn/machine-learning.
Often I hand-coded ML Algos implementations and tried out visualizing Decision Boundaries. My ML algos repo link: https://github.com/Vibhu1710/ML-Algos-Implementation
Deep Learning
Again used Hands-On ML for Deep Learning and parallely referred to Andrew Ng deep learning course https://www.coursera.org/learn/neural-networks-deep-learning?specialization=deep-learning
Back Prop article link that i found handy:
https://www.jeremyjordan.me/neural-networks-training/
Started out implementing shallow neural networks and understood how they worked in steps (epochs, what is the batch size etc).

Convolutional Neural network
I guess the best explanation and theory for this is here:
https://www.coursera.org/learn/convolutional-neural-networks?specialization=deep-learning
Implementation is a bit of a slow process here. Some articles that were stepping stones:
Transfer Learning implementation:
https://towardsdatascience.coma-comprehensive-hands-on-guide-to-transfer-learning-with-real-world-applications-in-deep-learning-212bf3b2f27a
At this point I found myself searching for implementations on kaggle.
One of the starter CNN basic level implementation to check out is this:
https://www.kaggle.com/uysimty/keras-cnn-dog-or-cat-classification
```
## Vikram Mondal
<a href="https://www.linkedin.com/in/mondal-vikram/">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>
Andrew NG : https://www.coursera.org/specializations/machine-learning-introduction

[![Generic badge](https://img.shields.io/badge/Batch-2021-<COLOR>.svg)](https://shields.io/)
```
https://www.kaggle.com/
https://www.codingninjas.com/?referralCode=JRQLA
Kirill Eremenko : https://www.udemy.com/course/machinelearning/

```
## Aayush Makkar
<a href="linkedin.com/in/aayushmakkar-pec">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>
2) Sites to keep track of the latest trends in AI and Machine Learning :

[![Generic badge](https://img.shields.io/badge/Batch-2021-<COLOR>.svg)](https://shields.io/)
```
Andrew NG’s stanford machine learning course to study in depth mathematics in machine learning. Go for as many guided projects as possible from coursera, pick up any random course for specific topic from udemy or go for complete ml track from Coding ninjas. After you are confident enough, start doing projects from kaggle. Random datasets can be found on kaggle,anazon datasets, UcI ml depository, etc.
```
## Pranab Jain
<a href="https://www.linkedin.com/in/pranab-jain-392442149/">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>
Analytics Vidhya : https://www.analyticsvidhya.com

[![Generic badge](https://img.shields.io/badge/Batch-2021-<COLOR>.svg)](https://shields.io/)
```
First Phase (Mostly Theory)
1. Linear Algebra
https://www.coursera.org/learn/linear-algebra-machine-learning
2. Calculus
https://www.coursera.org/learn/multivariate-calculus-machine-learning
3. Statistics
https://www.edx.org/course/introduction-probability-science-mitx-6-041x-2
4. Algorithms
https://www.coursera.org/learn/algorithms-part1
https://www.coursera.org/learn/algorithms-part2
Second Phase (Mostly Practical)
5. Data Science & Python
https://www.coursera.org/learn/python-data-analysis?specialization=data-science-python
6. Data Visualization
https://www.coursera.org/learn/python-plotting?specialization=data-science-python
7. Machine Learning
https://www.coursera.org/learn/machine-learning (After this you can start kaggle competitions)
8. Deep Learning
https://www.coursera.org/specializations/deep-learning
```
## Komal
Towards Data Science : https://towardsdatascience.com

[![Generic badge](https://img.shields.io/badge/Batch-2021-<COLOR>.svg)](https://shields.io/)
```
I started learning machine learning from coursera Introduction to machine learning course by andrew ng. Then udemy AtoZ Machine learning course. After this one can do project oriented courses or individual/team ML projects. Kaggle is best place to start.
```
## Hamza Ali Rizvi
<a href="https://www.google.com/url?sa=t&source=web&rct=j&url=https://in.linkedin.com/in/hamza-ali-rizvi-643251148&ved=2ahUKEwigucC0_pjvAhXUzDgGHbRtAc0QFjAAegQIBBAD&usg=AOvVaw24-9JNnsqInKEHeEtsV2HQ">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>
3) Great Youtube Channels for Learning ML :

[![Generic badge](https://img.shields.io/badge/Batch-2021-<COLOR>.svg)](https://shields.io/)
```
1) Learn Python3 the Hard Way by Shaw
2) Pandas, Matplotlib and Numpy courses on Kaggle.
3) Datacamp course on Introduction to Machine Learning.
4) Deep Learning with Tensorflow specialisation on Coursera by Deeplearning.ai
5) Computational Linear Algebra by fast.ai
6) Statquest YouTube channel by Josh Starmer
```
## Shubh Ashish
<a href="https://www.linkedin.com/in/shubh-ashish-a4a415190/">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>
Statquest with Josh Starmer : https://www.youtube.com/@statquest

[![Generic badge](https://img.shields.io/badge/Batch-2023-<COLOR>.svg)](https://shields.io/)
CodeBasics : https://www.youtube.com/@codebasics

Krish Naik : https://www.youtube.com/@krishnaik06

Yannic Kilcher : https://www.youtube.com/@YannicKilcher

```
Exploratory data analysis :
Loads of tutorials are present online. I followed this one:
https://www.udemy.com/course/python-for-data-science-and-machine-learning-bootcamp/

Machine Learning Algorithms :
Followed Jose Portilla’s (above) and Andrew NG’s courses:
https://www.coursera.org/learn/machine-learning
Josh Starmer’s wonderful explanation for topics like PCA, clustering, etc. helped, too:
https://www.youtube.com/c/joshstarmer
Tried implementing everything.

Deep Learning :
Again, Andrew NG’s Deep Learning specialization:
https://www.coursera.org/learn/neural-networks-deep-learning?specialization=deep-learning
And loads of towardsdatascience.com articles.

Convolutional Neural Networks :
Andrew NG, again:
https://www.coursera.org/learn/convolutional-neural-networks?specialization=deep-learning
Tried implementing stuff, with help of towardsdatascience.com articles, every now and then. Did the generic MNIST classification and tried a hand on the Kaggle Dog-vs-Cat dataset.

Recurrent Neural Networks :
Andrew NG’s got you covered:
https://www.coursera.org/learn/nlp-sequence-models?specialization=deep-learning
This, of course, was followed by hands-on implementation, with article reading from towardsdatascience.com and analyticsvidhya.com

Natural Language Processing :
Got some ideas from Jose’s course. Read many articles. Implemented and understood stuff like CountVectorization.
Did a basic task of sentiment analysis. (Many datasets on Kaggle.)
```
## Bavesh Kumar
<a href="https://www.linkedin.com/in/bhavesh-kumar-9ab7061b1/">

## Shrinjoy Mitra
<a href="https://www.linkedin.com/in/shrinjoy-mitra-3449861a5/">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>

[![Generic badge](https://img.shields.io/badge/Batch-2023-<COLOR>.svg)](https://shields.io/)
[![Generic badge](https://img.shields.io/badge/Batch-2024-<color>.svg)](https://shields.io/)
```
Exploratory data analysis :
https://www.coursera.org/learn/python-data-analysis
https://www.udemy.com/course/python-for-data-science-and-machine-learning-bootcamp/
(first few modules cover data analysis and visualization part)
https://www.kaggle.com/search?q=tag%3A%22exploratory+data+analysis%22 (Practice)

Machine Learning Algorithms :
To Learn Machine Learning Underlying concepts and mathematics follow
Andrew NG course (Stanford University) on Coursera.
https://www.coursera.org/learn/machine-learning
(but it’s in matlab so just learn concepts and to apply algorithms using python follow Jose Portialla’s course)
https://www.udemy.com/course/python-for-data-science-and-machine-learning-bootcamp/

Scratch Implementation of ML algorithms
(https://github.com/eriklindernoren/ML-From-Scratch/tree/master/mlfromscratch)

Edureka and Codebasics channel on youtube can also help!!

Deep Learning :

DeepLearning.AI’s Deep Learning Specialization covers almost everything.
Specialization Link
1st Course:- Build a neural Network from scratch
2nd Course:- Improving bare minimum model by tuning
3rd Course:- Best practices to follow in DL/ML.
4th Course:- Convolution Neural Nets
5th Course:- Recurrent Neural Nets.
Specialization has tons of assignments and projects so go for it.
To implement DL with Python you can go for Tensorflow it’s documentation is extremely great.
(https://www.tensorflow.org/)

Towardsdatascience.com, Medium.com, MachineLearningMastery all are always there to help with the implementation part.

Natural Language Processing :
Basics In Jose’s Course.
1)Python Basics:-
https://www.youtube.com/watch?v=rfscVS0vtbw

2)Data Structures and Algorithms:-
https://www.youtube.com/watch?v=pkYVOmU3MgA

3)Machine Learning:-
https://www.youtube.com/watch?v=GwIo3gDZCVQ

4)Deep Learning:-
https://www.youtube.com/watch?v=CS4cs9xVecg&list=PLkDaE6sCZn6Ec-XTbcX1uRg2_u4xOEky0

5)Linear Algebra for ML:-
https://www.youtube.com/watch?v=rSjt1E9WHaQ&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab

6)Kaggle Learn:-
https://www.kaggle.com/learn

7)Datasets:-
https://www.kaggle.com/datasets

Basics In Jose's Course.
For more on Text Mining and NLP check out
Applied Text Mining in Python course on Coursera by Michigan University.

Research Papers Look-UP :
https://analyticsindiamag.com/8-open-access-resources-for-ai-ml-research-papers/
```

## Parikh Goyal
<a href="https://www.linkedin.com/in/parikh-goyal-errpv/">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>

[![Generic badge](https://img.shields.io/badge/Batch-2022-<COLOR>.svg)](https://shields.io/)
[![Generic badge](https://img.shields.io/badge/Batch-2022-<color>.svg)](https://shields.io/)
```
Neural Networks
1) Stanford lecture series by Andrej Karpathy (Neural networks):
https://www.youtube.com/playlist?list=PLkt2uSq6rBVctENoVBg1TpCC7OQi31AlC

2) Hackerearth ML & DL monthly hackathons (Learn as you do)

3) NLP and GANs:
https://github.com/ibrahimjelliti/Deeplearning.ai-Natural-Language-Processing-Specialization

3) Practice on Google Colab (Easy to use and experiment)

4) Tensorflow2-GPU easy installation: https://towardsdatascience.com/tensorflow-gpu-installation-made-easy-use-conda-instead-of-pip-52e5249374bc
```

## Jyoti prakash Rout
<a href="https://www.linkedin.com/in/jyoti-prakash-rout">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>

[![Generic badge](https://img.shields.io/badge/Batch-2024-<COLOR>.svg)](https://shields.io/)
[![Generic badge](https://img.shields.io/badge/Batch-2024-<color>.svg)](https://shields.io/)
```
100% free machine learning courses:

- MIT 6.S191 Introduction to Deep Learning
- DS-GA 1008 Deep Learning
- UC Berkeley Full Stack Deep Learning
- UC Berkeley CS 182 Deep Learning
- Cornell Tech CS 5787 Applied Machine Learning

Top-notch. Google them. Pick one. Finish it.

```

## Rohit Bishla
<a href="https://www.linkedin.com/in/rohit-bishla-6a3a68202/">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>

[![Generic badge](https://img.shields.io/badge/Batch-2024-<COLOR>.svg)](https://shields.io/)
[![Generic badge](https://img.shields.io/badge/Batch-2024-<color>.svg)](https://shields.io/)
```
Some good free courses.
https://learndigital.withgoogle.com/digitalgarage/course/machine-learning-crash-course
Expand All @@ -283,6 +157,50 @@ https://www.udacity.com/course/aws-machine-learning-foundations--ud065
https://www.udacity.com/course/intro-to-tensorflow-for-deep-learning--ud187
https://www.udacity.com/course/machine-learning-unsupervised-learning--ud741
https://www.udacity.com/course/reinforcement-learning--ud600
```
```

<br />
## ML/DL Resources Contributor
<a href="https://github.com/Aujasyarajput18">
<img align="left" width="82px" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>
[![Generic badge](https://img.shields.io/badge/Batch-2025-<color>.svg)](https://shields.io/)
```
### Advanced ML/DL Resources

#### Large Language Models (LLMs)
- Hugging Face NLP Course: https://huggingface.co/course/chapter1/1
- Stanford CS224N: Natural Language Processing with Deep Learning: http://web.stanford.edu/class/cs224n/
- LLM University by Cohere: https://docs.cohere.com/docs/llmu
- Practical guides on fine-tuning LLMs: https://www.deeplearning.ai/short-courses/finetuning-large-language-models/
- OpenAI GPT best practices: https://platform.openai.com/docs/guides/gpt-best-practices

#### Transformers Architecture
- Illustrated Transformer by Jay Alammar: http://jalammar.github.io/illustrated-transformer/
- Attention Is All You Need (Original Paper): https://arxiv.org/abs/1706.03762
- The Annotated Transformer: http://nlp.seas.harvard.edu/annotated-transformer/
- Hugging Face Transformers Documentation: https://huggingface.co/docs/transformers/index
- Stanford CS25: Transformers United: https://web.stanford.edu/class/cs25/

#### Generative Adversarial Networks (GANs)
- GAN Lab - Interactive Visualization: https://poloclub.github.io/ganlab/
- Stanford CS236: Deep Generative Models: https://deepgenerativemodels.github.io/
- GAN Specialization by DeepLearning.AI: https://www.coursera.org/specializations/generative-adversarial-networks-gans
- PyTorch GAN Tutorial: https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html
- Papers with Code - GANs: https://paperswithcode.com/methods/category/generative-adversarial-networks

#### Neural Network Architectures
- Deep Learning Architectures Visual Guide: https://www.asimovinstitute.org/neural-network-zoo/
- ResNet Paper (Deep Residual Learning): https://arxiv.org/abs/1512.03385
- EfficientNet: Rethinking Model Scaling: https://arxiv.org/abs/1905.11946
- Vision Transformers (ViT): https://arxiv.org/abs/2010.11929
- CNN Explainer - Interactive Visualization: https://poloclub.github.io/cnn-explainer/

#### Additional Resources
- Papers with Code: https://paperswithcode.com/
- Arxiv Sanity Preserver: http://www.arxiv-sanity.com/
- Distill.pub (Visual ML explanations): https://distill.pub/
- Two Minute Papers (YouTube): https://www.youtube.com/@TwoMinutePapers
```

<!--
-->