Ideas from books, articles & podcasts.
Many machine learning textbooks present students with a chart that shows a tradeoff between model interpretability and model accuracy. This is a heuristic, but many students come away thinking that this tradeoff is as strict as a law of physics.
MORE IDEAS FROM THE SAME ARTICLE
A national effort was undertaken to build Algorithms to predict which pneumonia patients should be admitted to hospitals and which are treated as outpatients. Only by interpreting the model was a crucial problem discovered and avoided. Understanding why a model makes a prediction can literally be...
An ordinary least squares (OLS) model generates coefficients for each feature. These coefficients are signed, allowing us to describe both the magnitude and direction of each feature at the global level. For local interpretability, we need only multiply the coefficient vector by a specific featur...
In the middle of the accuracy-interpretability spectrum are random forests. We’ve often seen them described as “black boxes,” which we think this is unfair — maybe “gray” but certainly not “black”!
Random forests are collections of decision trees, like the one drawn below. The splits in eac...
As the hottest topic in machine learning over the past decade, we’d be remiss if we didn’t mention neural networks. Hailed for outstanding accuracy in difficult domains like image recognition and language translation, they’ve also generated criticism for lacking interpretability.
MORE LIKE THIS
The biggest problem, thoug h, is that models like this one are performed only on a single task. Future tasks require a new set of data points as well as equal or more amount of resources.
Transfer learning is an approach in deep learning (and machine learning) where knowledge is ...
published 1 ideas
The ability for an organ to take photons from the outsight world, focus them, and then convert them into electrical signals is pure awesomeness! But what’s even more awesome is the organ behind your eyeballs — the brain!
The brain is able to take those electrical signals, convert them into ...
❤️ Brainstash Inc.