Jupyter notebooks on Machine Learning for non CS majors .
Which machine learning algorithms should you use for your project or research? There are already several automatized programs that apply machine-learning algorithms to data. As designed, those methods do not use optimal parameters nor do they use recent technology. In this project, we aim to give several examples of algorithms and applications to help you identify the method most suitable for your problem, while understanding how to tune the parameters of the algorithm. This will be an important difference to note if you are interested in research or optimizing solutions to problems. Just in case you only want a quick solution without worrying whether or not it is optimal, you may prefer to use automatized methods instead. We will mention a couple of those methods in the corresponding section.
Our goal is to make these notes accessible for non-CS majors, with plenty of examples that would help someone identify if a particular problem can be solved with a specific method.
Half of the lectures use Scikit-learn. The section on neural networks contains a lecture on Keras. For the advanced parts, we have lectures on Pytorch and Tensorflow.
We categorized the notebooks based on applications
We explain how images work in Python. We then introduce Artificial Neural Networks and CNN, as well as Style Transfer. Other methods, such as SOM or SVM are described as well.
The expository notes on Potential Energy Surface and GARField.
Both the Bayesian method and the MCMC method are mentioned.
Non negative tensor factorization.
We have tutorials on IBM Q, D-Wave and Qiskit.
Select the topics that you are interested in.
Contributors of the Machine Learning notebooks
Hello, I am Peter. My research interests are: Engineering, Optimization, Hardware, Modeling and Simulation. My training is in Mechanical Engineering and Material Science.
Hello, I am Alex. My research interests are Financial Mathematics. My training is in Physics.
Join our Slack channel; there you can give us suggestions or contribute.
We have a Machine Learning channel. If you have any suggestions or questions, you can chat with the authors of this website, as well as learn about our future projects.
Join our slack channel
College of Engineering
Michigan State University
