ketan agrawal

computer vision
Last modified on September 11, 2021

Links to “computer vision”

compositionality (A machine learning example of compositionality)

is that a computer vision model’s early layers will implement an edge detector, curve detector, etc., which are modular pieces that are then combined in various ways by higher-level layers to form dog detectors, car detectors, etc.

progression from low-level to high-level features in a CNN.

But ultimately the ways in which machine learning models, at the moment, can “intelligently” combine different pieces and parts is limited. See the tweet about DALL-E trying to stack blocks, bless its heart:

One step towards compositionality is the idea of neuro-symbolic models. Combining logic-based systems with connectionist methods.