I meant to read this paper for a long time and finally got around to it. Paper link: https://arxiv.org/abs/2003.05161v2 Laura Ruis is the main author, I hope she goes on to do more work in this “general direction” 🙂 Jacob Andreas of NTM fame is a co-author, awesome! Brenden Lake who does tons of interesting… Continue reading My notes on ”A Benchmark for Systemic Generalization in Grounded Language Understanding”
Tag: composability
Examining concepts through different filters
I think the human mind an autonomous interlinked model building database of the world. I define models and concepts to be the same thing. One important aspect of this system that has been nagging me is the idea that the human mind can examine ideas/models/concepts from different filters. In my article about the mind as… Continue reading Examining concepts through different filters
The first models a human infant might create to model their world
If human mind is an autonomous interlinked model building system, then what would the first models for an infant look like? The list below is a thought experiment into what those first models would look like. Lines and edgesThey can be any lengthThey can be varying widthsNot 100% straight Eye movementCan move my eye and… Continue reading The first models a human infant might create to model their world
The human mind is an autonomous interlinked model building database of the world
My definition of intelligence has become refined over time. In my article about the the human mind being a simulation engine, I already wrote out some of the points I am going to make, but my thinking has on the topic has become more clear. The human mind is composed of tens of thousands of… Continue reading The human mind is an autonomous interlinked model building database of the world
Abstract Structure Primitives
It is a fact that there are specific neurons in the retina that take in the raw input from the eye and detect specific features such as red, blue, lines,edges, and more. These features (or objects) are sent further up in the processing center of the mind to form more complex objects like buckets, cars,… Continue reading Abstract Structure Primitives
Comparing random concepts together
Can we compare any random concepts? Let’s try doing it with two objects. Car Pencil moves (with human intervention) doesn’t move fast slow large small dangerous in multiple ways relatively safe object boxy long large and heavy skinny sort of portable portable solid and stable easily broken mostly metal non-metals How are they similar: man… Continue reading Comparing random concepts together
Compositional vs composable in AGI research
These 2 terms are talked often in software development, philosophy of language, and machine learning. Sometimes they are used interchangeably and I’m not sure if that is on purpose or not, but their definitions are related and similar, but with slight differences. Compositional means that the meaning of the whole expression or structure of something… Continue reading Compositional vs composable in AGI research
adjectives and nouns are composable
You can take any adjective and apply it to any noun and although the result may not make sense, the mind can imagine or change the meaning enough that the combination could make sense. Examples: fast dog – it can run faster than average ugly dog – looks uglier than the average dog, subjective. smart… Continue reading adjectives and nouns are composable