Sometimes I find it useful to be able to run Python commands right from the command line (without entering a Python console). Here are some ways I’ve found it useful.
The most frequently used evaluation metric for object detection is “Average Precision (AP)”. But, despite the attempts of well-intentioned researchers to create a single metric for comparing models, no single metric is the right one for all the cases. Thus the landscape of metrics has become filled with small variations on the idea of average precision. This post aims to clarify those variations.
I find that sometimes the best way to understand a topic is to see it in action. That can be tricky for some topics, like computer vision and deep learning, so I created this page to aggregate some of my favorite visualizations in these fields. I hope to continuously add to this page. Let me know if you have any suggestions for what made an idea click for you!
Selecting and evaluating a dataset to use for training a machine learning model is an essential step in the process. It’s far more important than having the latest architecture or doing the most detailed hyperparameter tuning. It’s probably the most important aspect of the process other than asking the right questions in the first place.
This post is an introduction to principal component analysis (PCA). It was originally written to accompany a presentation to the NOVA Deep Learning Meetup.
This post aims to explore decision trees for the NOVA Deep Learning Meetup. It is based on chapter 8 of An Introduction to Statistical Learning with Applications in R by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. It also discusses methods to improve decision tree performance, such as bagging, random forest, and boosting. There are two posts with the same material, one in R and one in Python.
This post aims to explore decision trees for the NOVA Deep Learning Meetup. It is based on chapter 8 of An Introduction to Statistical Learning with Applications in R by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. It also discusses methods to improve decision tree performance, such as bagging, random forest, and boosting. There are two posts with the same material, one in R and one in Python.