KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #typescript #ai-agent #developer-tools #claude-code #codex #deepseek-harness #ai-agents #react #mcp #rust

How-to-learn-ML-for-humans

★ 72 Open GitHub ↗

A learning path with tutorials for learning AI/ML

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# How to learn ML for humans & :alien:

Learning path for AI/ML that worked for me :sparkles:

## Programming Knowledge

Programming knowledge is a must obviously.

### Learn Python :snake:

1. Python basics : variables, conditions, loops..etc..etc..etc
2. But most importantly installing packages, importing, using.
3. Writing methods and using decorators.
4. Object oriented python: class, inheritance.

:bulb: The book [automate the boring stuff](https://automatetheboringstuff.com) is a good resource.

:crystal_ball: [Articles](https://pythonprogramming.net) and [Youtube videos](https://www.youtube.com/user/sentdex) by [Sentdex](https://twitter.com/Sentdex) is awesome!

### Install and setup stuffs :construction:

Things you need and need not.

1. A :computer: running any OS :white_check_mark:
2. A high end GPU :x:
3. Python installed [directly](https://www.python.org) or using [anaconda](https://www.anaconda.com)/[miniconda](https://docs.conda.io/en/latest/miniconda.html#) :white_check_mark:
4. A heavy IDE like pycharm or spyder :interrobang:
5. Use light weight IDEs like [VScode](https://code.visualstudio.com) :white_check_mark:

:bulb: Make sure you integrated installed python with your IDE and [intellisense](https://docs.microsoft.com/en-us/visualstudio/ide/using-intellisense?view=vs-2019) works fine.

#### :full_moon_with_face: For god sake don't use notepad to code!

### Next steps with programming (recommended)
Do the following to take python learning to the next level
1. Build a python project and opensource.
2. Learn building a backend web app using [flask](https://flask.palletsprojects.com/en/1.1.x/)/[django](https://www.djangoproject.com)/[responder](https://responder.kennethreitz.org/en/latest/)

## ML algorithms and its Mathematics :1234:

### Truth about the maths
You need basic knowledge in the following mathematics areas for ML
1. Algebra
2. Probability
3. Differentiation

:bulb: Use your school/college text books to brush up maths skills.

### Learning algorithms
Use various resources in the internet to understand the concepts of following machine learning algorithms

1. Linear regression
2. Logistic regression.
3. Kmeans and KNN.
3. Neural networks.
4. Deep neural networks.

And the lists goes on...

:bulb: Check out this [awesome machine learning tutorials](https://github.com/ujjwalkarn/Machine-Learning-Tutorials) repo.

:crystal_ball: Checkout [d2l](http://d2l.ai/) for learning algorithm implementation

#### Pro tip : Learn the maths on the go. Means check out the maths part when you get stuck instead of going through maths first.

## Implementing the algorithms :woman_technologist:

This is an important part. Learning how to implement ML algorithms :boom:
- Try to implement the ML algorithms with vanilla python and the following libraries.

### Packages to use
1. [Numpy](https://numpy.org) : For nuemerical computations
2. [Pandas](https://pandas.pydata.org) : For data preproessing 
3. [Matplotlib](https://matplotlib.org) : For plotting the data

## ML libraries and doing projects
Now you can learn an ML library and start doing projects in ML.

### Various ML libraries

1. [Sklearn](https://scikit-learn.org/stable/tutorial/index.html) : ML library with classic machine learning algorithms
2. [Tensorflow](https://www.tensorflow.org/tutorials) & [keras](https://keras.io/getting_started/intro_to_keras_for_engineers/) : DL libary with keras as high level API
3. [Pytorch](https://pytorch.org/tutorials/) : DL library built built focusing for research.

and the list goes on...

:bulb: You can start with any of the libraries. I would recommend to use offical docs and tutorials to learn!

## Steps for doing ML project :star:
Do an ML project to evaluate and show off your learning. Following are some of the steps in doing ML projects.

### 1. Find out a problem you can solve using ML.
![alt text](https://scienceonblog.files.wordpress.com/2016/06/new_element.jpg?w=816)

### 2. Figure out the logic + ML pipeline you can build for solving the problem.
![alt text](https://www.memezero.com/download/QA068L.jpg)

### 3. Search the internet for the dataset you need.
A lot of publicly available datasets can be found in the internet. Two popular sources are,
- [Google dataset search](https://datasetsearch.research.google.com)
- [Kaggle datasets](https://www.kaggle.com/datasets)

### 4. Cry out loud when you don't find the dataset for your specific problem.
![alt text](https://www.malayalamplainmemes.download/images/the-great-father-mammootty-infdb/full)

### 5. Collect dataset using crowd source or other means

![alt text](https://www.mathrubhumi.com/polopoly_fs/1.4405146.1577772498!/image/image.png_gen/derivatives/landscape_894_577/image.png)

- Build an app for collecting dataset and share with friends
- Use google form for collecting data
- Scrap the dataset from various websites (be careful about copyright)
- Connect with authorities having data like govt to collaborate.

### 6. Train. Evaluate. Tune. Repeat.
- Use pretrained models or build ML models.
- Preprocess the dataset collected.
- Train and test the model.
- Tune the hyper params and repeat training and testing.
- Wrap it with a web app or mobile and app
- Don't forget to open source or publish your project.

## Next steps
AI/ML is growing fastly day by day. Focusing on a particular area of AI after learning and doing the foundational elements would be nice!

:bulb: Following are some of the interesting areas in AI

###  On device AI/ML
Instead of sending inputs from client like images, speech..etc to the ML model in server, on device AI/ML helps to do the inference in client side with the help of AI chips (like bionic chip in iPhone) and libraries like,
- [Core ML](https://developer.apple.com/documentation/coreml)
- [Tensorflow lite](https://www.tensorflow.org/lite)
- [Pytorch mobile](https://pytorch.org/mobile/home/)

### Privacy preserved AI/ML

Techniques like federated learning helps to train models on device and share the model to the servers(and other clients) instead of sending data to the servers and training there. Means your data is private and safe!

- [Openmind pysyft](https://www.openmined.org)
- [Tensorflow Federated](https://www.tensorflow.org/federated)

### Computer Vision and NLP
Two major fields in AI/ML. Learn both or specialise in one :information_desk_person:

### Robotics and edge computing

Deep reinforcement learning techniques and various other AI/ML algorithms are used in applications like robotics, automation and IoT.

- [OpenAI gym](https://gym.openai.com)
- [Tensorflow lite](https://www.tensorflow.org/lite) for Raspberry Pi and microcontrollers

Thank you. Happy Learning !

How-to-learn-ML-for-humans

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README