If you are like me and try to follow the principles of DRY, KISS, Deaign Patterns, and Occam’s Razor then this repo is for you!
Occam’s Razor: The best model that fits your data is usually the best.
As an AI/ML engineer, you should be willing to settle for “good enough” rather than trying to find the “best” model/approach.
Scrum is a popular project management approach but not really a software development methodology [1]. I prefer using an iterative, agile feature-driven development (FDD) methodology where team members are able to work independently [2].
This repo contains notes from various articles and other resources on a variety of topics in Artificial Intelligence (AI) and Machine Learning (ML).
This is a work in progress (just getting started), so there is still# a lot missing and the content is changing.
NOTE: The Medium and TowardsDataSciene articles can be viewed in a browser Private tab.
TODO: Add items
Concurrency - Mutliprocessing vs Multithreading
Exploratory Data Analysis (EDA)
Discrete Probability Distributions
SMOTE for Imbalanced Classification
Generative Adversarial Network (GAN)
Long Short-Term Memory Networks (LSTMs)
Natural Language Understanding
Applied Machine Learning Process
Imbalanced Classification Framework
TODO: Add items
Statistics for Machine Learning
[1] I. Sommerville, Software Engineering 10th ed., Pearson, ISBN: 978-0133943030, 2015.
[2] P. Bourque and R. E. Fairley, Guide to the Software Engineering Body of Knowledge (SWEBOK) v. 3, IEEE, 2014.