๐ Learn ML with clean code, simplified math and illustrative visuals. As you learn, work on interesting projects and share them on https://madewithml.com for the community to discover and learn from!
As you learn ML, it's important to work on projects, so check out Made With ML for inspiration and to create a profile to showcase your own projects!
๐ Discover ML projects with code on niche topics that interest you.
๐ Build projects of your own and share it with the community.
๐ฉโ๐ป Showcase your profile on your resume or apply directly to ML managers.
NOTE: Everyone has Coursera, Kaggle, and fastai on their resumes so differentiate yourself by showcasing your projects. Check out this article on how to stand out with a MWML profile.
Should I pick TensorFlow or PyTorch? Choice of framework doesnโt matter! Check out the basic lessons and choose what you find more intuitive/suitable but the most important thing is to work on projects and share them with the community.
Do I need to know both TensorFlow or PyTorch? It is very important to at least know how to read both
frameworks because cutting edge research continues to use both frameworks. Luckily, they're both very easy to learn and very easy to rewrite in the other framework.
๐ป These are not a set of tutorials where we just load a bunch of packages and apply it on preloaded datasets. We explain every concept in the notebooks with clean code, simple math and visualizations to make them as intuitive as possible.
๐ If you prefer Jupyter Notebooks or want to add/fix content, check out the notebooks directory.
Learn how to collect data and organize it using SQL.
Showcase your applications using a simple Boostrap front-end.
๐ Web scraping
๐ SQL
๐จ Bootstrap
Scaling
Standardize and scale your ML applications with Docker and Kubernetes.
Deploy simple and scalable ML workflows using MLFlow.
๐ณ Docker
๐ข Kubernetes
๐ MLFlow
Advanced
Dive into architectural and interpretable advancements in neural networks.
Implement state-of-the-art NLP techniques.
Learn about popular deep learning algorithms used for generation, time-series, etc.
๐ง Attention
๐ Language Modeling
๐ค Transformers
๐คฏ SHA-RNN
๐ญ Generative Adversarial Networks
๐ฎ Autoencoders
๐ท๏ธ Graph Neural Networks
โฑ Temporal CNNs
๐ Reinforcement Learning
๐ฏ One-shot Learning
๐ฑ Bayesian Deep Learning
๐ Causal Inference
Topics
Learn how to use deep learning for computer vision tasks.
Implement techniques for natural language tasks.
Derive insights from unlabeled data using unsupervised learning.
๐ธ Image Recognition
๐ผ๏ธ Image Segmentation
๐จ Image Generation
๐ Text classification
๐ฌ Named Entity Recognition
๐ง Knowledge Graphs
๐๏ธ Topic Modeling
๐ก Clustering
๐ต๏ธ Anomaly Detection
Miscellaneous
Learn about miscellaneous topics that are at the forefront of ML research and application.
โฐ Time-series
๐ค Speech Recognition
๐ Recommendation Systems
๐๏ธ Interpretability
โ๏ธ Model Compression
โ๏ธ Data Annotation
โ๏ธ Imbalanced Datasets
๐ป Missing Values
๐ Data Visualization
Statistical Learning
Learn the basics of statistics that paved the way for all the topics above.
Implement statistical learning methods in scikit-learn.
๐งช Hypothesis Testing
โค๏ธ Maximum Likelihood Estimation
๐ถ Naive Bayes
๐ Linear Regression
๐ Logistic Regression
๐ฆบ Support Vector Machines
๐ณ Random Forests
๐ Nearest Neighbors
๐ฟ Gaussian Processes
๐ฅ Matrix Decomposition
๐ฉ Hidden Markov Models
๐ฆ Survival Analysis
About
๐ Learn ML with clean code, simplified math and illustrative visuals. As you learn, work on interesting projects and share them on https://madewithml.com for the community to discover and learn from!