A Surprising Development in the Study of Multi-layer Parameterized Graphical Function Approximators

As a programmer and epistemology enthusiast, I've been studying some statistical modeling techniques lately! It's been boodles of fun, and might even prove useful in a future dayjob if I decide to pivot my career away from the backend web development roles I've taken in the past.

More specifically, I've mostly been focused on multi-layer parameterized graphical function approximators, which map inputs to outputs via a sequence of affine transformations composed with nonlinear "activation" functions.

(Some authors call these "deep neural networks" for some reason, but I like my name better.)

It's a curve-fitting technique: by setting the multiplicative factors and additive terms appropriately, multi-layer parameterized graphical function approximators can approximate any function. For a popular choice of "activation" rule which takes the maximum of the input and [...]

---

Outline:

(00:07) A Surprising Development in the Study of Multi-layer Parameterized Graphical Function Approximators

(04:00) Multi-layer Parameterized Graphical Function Approximators Have Many Exciting Applications

(06:05) An Example of Applying Multi-layer Parameterized Graphical Function Approximators in Success-Antecedent Computation Boosting

(10:35) Risks From Learned Approximation

---

First published:

Source:

Linkpost URL:
http://zackmdavis.net/blog/2024/03/deep-learning-is-function-approximation/

Narrated by TYPE III AUDIO.