Learn Machine Learning in 3 Months
===

## Learn Machine Learning in 3 Months (PyTorch 🔥 Curriculum)

##### Overview

This is the Curriculum for [Learn Machine Learning in 3 months (PyTorch Curriculum)](https://youtu.be/dS2HYPY7T-4) by Siraj Raval on Youtube. Beginners to Python will learn to build, train, deploy, scale & maintain modern Machine learning & Deep learning models. Each weekly assignment will teach you how to use a new concept or tool, like Docker, PyTorch, or Transformer Models. The Final Project will integrate everything you've learned into a Self Driving Car simulation. After completion, start an ML startup or find relevant work in the field. Together as a learning community, we're going to help each other succeed!

##### Components
- 🤝 Social: Join our [Discord](https://discord.gg/zgEJxeYA2X) channel to find a study buddy
- ✨ Interactive: Every resource is web-based with user input
- 🧑‍🎓 Beginner-Friendly: Build weekly projects without dependencies thanks to [codespaces](https://github.com/codespaces)
- 🤖 Project-Based: Learn Computer Vision, Natural Language Processing, Time Series Forecasting, Audio Processing, & Recommender Systems

##### Tools Used
- [Python](https://www.python.org/downloads/), [Pip](https://pip.pypa.io/en/stable/installation/), [Numpy](https://numpy.org/), [Pandas](https://pandas.pydata.org/), [Seaborn](https://seaborn.pydata.org/), [Matplotlib](https://matplotlib.org/), [PyTorch](https://pytorch.org/), [Replit](https://replit.com/), [SQL](https://www.w3schools.com/sql/), [Jupyter](https://jupyter.org/), [Streamlit](https://streamlit.io/), [Gradio](https://www.gradio.app/), [HuggingFace](https://huggingface.co/docs), [Airflow](https://airflow.apache.org/), [GCP](https://cloud.google.com/), [AWS](https://aws.amazon.com/), [Spark](https://spark.apache.org/), [Scikit-learn](https://scikit-learn.org/stable/), [Prometheus](https://prometheus.io/), [Evidently](https://www.evidentlyai.com/), [Grafana](https://grafana.com/), [Flask](https://flask.palletsprojects.com/en/2.2.x/), [Prefect](https://www.prefect.io/), [MongoDB](https://www.mongodb.com/), [Postgres](https://www.postgresql.org/), [Kafka](https://kafka.apache.org/), [Terraform](https://www.terraform.io/), [RL-Baselines](https://github.com/DLR-RM/rl-baselines3-zoo), [Unity](https://unity.com/), [W&B](https://wandb.ai/site), [Kubernetes](https://kubernetes.io/), [DBT](https://www.getdbt.com/)

##### Learning Tools
- [Elicit](https://elicit.org) to answer questions
- [ExplainPaper](https://explainpaper.com) to explain math
- [Summari](https://summari.com) to explain text
- [Spaces](https://huggingface.co/spaces) to sample demos
- [CoPilot](https://githubnext.com/projects/copilot-labs/) to explain code

## Month 1 - Machine Learning 🔥

Week 1: [Python Fundamentals (Allen Downey)](https://allendowney.github.io/DSIRP/index.html)

[Assignment](https://allendowney.github.io/DSIRP/pagerank.html): Build a Python search function for Researchers. Given a list of search terms, return a list of pages sorted by relevancy. Modify the example with your own alpha parameter.

Week 2: [Mathematics of Machine Learning (xaktly.com)](http://www.xaktly.com/XMathMain.html)

[Assignment](http://www.xaktly.com/ProbabilityBayesian.html): Solve the Bayesian probability problem for Supply Chain using pencil & paper. Do so after completing each full section on Calculus, Probability, Statistics, & Matrices.

Week 3: [Data Analysis (Kaggle)](https://www.kaggle.com/learn)

[Assignment](https://www.kaggle.com/datasets/atharvaingle/crop-recommendation-dataset): Build a data visualization iPython notebook for Farmers. Search Kaggle for an agricultural dataset, then visualize it 3 different ways for comparison & further analysis.

Week 4: [Machine Learning Techniques (Cyrille Rossant)](https://github.com/ipython-books/cookbook-2nd)

[Assignment](https://github.com/ipython-books/cookbook-2nd/blob/master/chapter08_ml/06_random_forest.md): Build a Random Forest Regression model for Real Estate. Clean, augment, & feature engineer a dataset to predict the price of houses next year in Boston

## Month 2 - Deep Learning 🔥🔥

Week 1: [Neural Networks (Interactive Dive into Deep Learning Book)](http://d2l.ai/)

[Assignment](https://github.com/ludobouan/pure-numpy-feedfowardNN/blob/master/example/Exploring_XOR_approximation.ipynb): Build a simple feedforward neural network for Retail. Upload the Jupyter Notebook to [Colab](https://colab.research.google.com/), modify input data, monitor how it effects accuracy

Week 2: [Transformers (HuggingFace Course)](https://huggingface.co/course/chapter1/1)

[Assignment](https://github.com/karpathy/minGPT/blob/master/mingpt/model.py): Build a conversational transformer for Mental Health therapy. Specifically, train Mini-GPT to have a therapeutic conversation by uploading it to Colab for training.

Week 3: [Diffusers (Fast.AI Course)](https://www.fast.ai/posts/part2-2022-preview.html)

[Assignment](https://huggingface.co/spaces): Build a design generator for Architects. Create a HuggingFace Space, select an existing image dataset, & create a web interface to generate designs.

Week 4: [Deep Reinforcement Learning (Simonini Thomas)](https://simoninithomas.github.io/deep-rl-course/)

[Assignment](https://colab.research.google.com/github/deepmind/mujoco/blob/main/python/LQR.ipynb#scrollTo=dDLihz5hk9Wt): Train a Humanoid Robot to walk in simulation within a Jupyter Notebook for Construction projects. Generate a 10 second video of the humanoid walking.

## Month 3 - Machine Learning Operations 🔥🔥🔥

Week 1: [Design (Made with ML Course)](https://madewithml.com/)

[Assignment](https://madewithml.com/courses/mlops/design/): Design a Medical Imaging Classification app for Doctors. Create the product requirements, design documentation, & project plan.

Week 2: [Development (Full Stack Deep Learning Course)](https://fullstackdeeplearning.com/course/2022/)

[Assignment](https://fullstackdeeplearning.com/course/2022/lab-7-web-deployment/) - Package a pretrained text recognition model into a TorchSript binary, wrap it in a serverless cloud function, & build a simple UI.

Week 3: [Production (DataTalks.CLub ML Ops ZoomCamp)](https://github.com/DataTalksClub/mlops-zoomcamp)

[Assignment](https://github.com/DataTalksClub/mlops-zoomcamp/blob/main/05-monitoring/homework.md) - Deploy a pretrained model for Traffic Prediction. Generate a report that detects any feature drift between model versions.

Week 4: [Data Engineering (DataTalks.CLub Data Engineering ZoomCamp)](https://github.com/DataTalksClub/data-engineering-zoomcamp/)

[Final](https://github.com/DataTalksClub/data-engineering-zoomcamp/tree/main/week_7_project) - Deploy a Self Driving Car Simulation app. This [Javascript](https://github.com/omuryildirim/before-evening) example is a great starting point. Integrate NLP, Computer Vision, Reinforcement Learning, & ML Ops.

---------------------

[Interview Preparation Study Guide](https://www.techinterviewhandbook.org/)

###### tags: `개인` `study` `MachineLearning`