Cookies on OyList

We use essential cookies to keep OyList working, and Google uses cookies to show and measure the ads on our lists. With your permission, Google Analytics cookies help us count visits and understand which pages are useful.

How we use cookies

Share

Embed
Share this list with friends or copy the link:

Items8

1

Google Machine Learning Crash Course

by curious_compiler  • 
Google Machine Learning Crash Course
Start here if you want to understand what a model is doing before you commit to a full semester of lectures. Short modules combine explanations, interactive figures, and exercises on topics such as linear regression and classification. Google recommends familiarity with Python, NumPy, and pandas, plus algebra and basic statistics. No prior machine learning is required.
More about Google Machine Learning Crash Course
2

Practical Deep Learning for Coders, fast.ai

by curious_compiler  • 
Practical Deep Learning for Coders, fast.ai
If you’d rather run a model early and work out why it behaves that way, start here. The first lessons have you build an image classifier and use notebooks alongside the videos. Fast.ai recommends about a year of coding experience, preferably Python, and high school math. The lectures and notebooks are free.
More about Practical Deep Learning for Coders, fast.ai
3

Machine Learning in Python With scikit-learn, Inria

by curious_compiler  • 
Machine Learning in Python With scikit-learn, Inria
Use this course to get better at deciding whether a model works. The self-paced material builds toward comparing estimators and testing them on data they were not trained on. You need to be able to write Python functions and import modules. Familiarity with NumPy, pandas, and Matplotlib helps, but Inria lists it as optional.
More about Machine Learning in Python With scikit-learn, Inria
4

Stanford CS229, Machine Learning

by curious_compiler  • 
Stanford CS229, Machine Learning
Choose Stanford’s public archive if you want to follow the math behind a method and then try an assignment. Recorded lectures, handouts, and assignments cover topics including regression, support vector machines, and clustering. You should already be able to write a nontrivial program and know basic probability and linear algebra.
More about Stanford CS229, Machine Learning
5

MIT 6.036, Introduction to Machine Learning

by curious_compiler  • 
MIT 6.036, Introduction to Machine Learning
Choose this for a university course you can work through in order. It connects supervised learning to ideas such as representation, overfitting, and generalization. Comfort reading Python and mathematical notation will make the material easier to follow. MIT lets you use the materials without enrolling, or enroll for free to track your progress.
More about MIT 6.036, Introduction to Machine Learning
6

Learning From Data, Caltech

by curious_compiler  • 
Learning From Data, Caltech
Use Caltech’s recorded course if you want to understand why fitting a dataset and learning a pattern are different. The lectures move through learning feasibility, training versus testing, and the role of model complexity. The site links to homework and lists basic probability, matrices, and calculus as prerequisites.
More about Learning From Data, Caltech
7

Statistical Learning With Python, Stanford Online

by curious_compiler  • 
Statistical Learning With Python, Stanford Online
Follow this alongside the authors’ Python textbook if you want a worked example to go with each concept. The course covers regression, classification, and resampling, and the corresponding book labs give you code to try. Familiarity with Python will make the labs easier to follow. Use the free course option on edX if you only need the learning material.
More about Statistical Learning With Python, Stanford Online
8

Machine Learning Zoomcamp, DataTalks.Club

by curious_compiler  • 
Machine Learning Zoomcamp, DataTalks.Club
Take this if your goal is a model someone else can actually use. The project material moves from framing a problem and testing a model to exposing it through an API. The videos and repository are available for self-study. The course expects programming experience and is a better fit if you can already use Python and basic Git.
More about Machine Learning Zoomcamp, DataTalks.Club

Comments