Artificial Intelligence is defined as the act of parameter estimation.
Toy example for Linear Regression
- Imagine if we want to predict the price of a choclate bar
- We feed in a bunch of bar weight vs. chocolate price data; that’s the training data
- Then, we come up with a model of the training data
- We then throw away the training data
Therefore, we can think of the model as a COMPRESSION of the training data; estimating parameters.
Bias in AI
It is the ability of AI as a TOOL that causes it a very big UNDOING.
Blueberry Muffin vs. Chuwawa
Its quite difficult to come with codified rules; yet, we can just ask for it to compressive