how a computer system could view a model from different angles research what are properties of models research examples of models that can be linked together. study SDRs more research using motor systems for models research who are the top relevant researchers and read all their works write up ideas on each neuron being full… Continue reading Ideas to research for a somatic data structure
Month: January 2022
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
Use a zettelkasten to amplify your thoughts
I remember when I ran across this blog post: https://blog.kewah.com/2021/write-more-but-shorter/ Then I read this blog post: https://critter.blog/2020/10/02/write-5x-more-but-write-5x-less/ Then I researched more and found this: https://writingcooperative.com/zettelkasten-how-one-german-scholar-was-so-freakishly-productive-997e4e0ca125 And then my writing exploded. A zettelkasten is a simple writing method that amplifies your writing , memory, thoughts, research, note taking, or any non-fiction writing you may want to… Continue reading Use a zettelkasten to amplify your thoughts
My research goal
AGI is a large field. My focus is to make a meaningful contribution to AGI research. While I do believe some form of AGI will be recreated in computers one day, I think it is improbable that we will see it in our lifetimes. I believe my goal is closer and attainable. I want to… Continue reading My research goal
Areas in artificial intelligence I am interested in researching
amodal representation language of thought sensorimotor system language composability grounded language learning moving up and down the abstraction ladder unsupervised learning causality surprise learning neuron ensemble communication abstract learning predictive coding / predictive processing free energy principal attention models feature extraction computational representations of emotion markov blankets
Research template
Why X is important History of X Famous papers about X Top researchers in X Examples of X in real life how would you test X: test suite, unit tests, formal test, etc definition of X explain X to a child how past iterations of X has failed compare and contrast X with other related… Continue reading Research template
Examples of concepts that are grounded in the physical world
All concepts have their root in the physical world. You could say they are grounded in the real world. The concept “rough”. We first learn about the concept “rough” from touching certain physical objects like wood, sandpaper, cement, etc. “Rough” means to have uneven or irregular surface. Later, people learn to apply “rough” to things… Continue reading Examples of concepts that are grounded in the physical world
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
We can brute force AGI with a realistic physics simulator
“An unknown, but potentially large, fraction of animal and human intelligence is a direct consequence of the perceptual and physical richness of our environment, and is unlikely to arise without it”. – John Locke (1632-1704) As we already know, AGI is probably the hardest problem mankind can work on and we do not have a… Continue reading We can brute force AGI with a realistic physics simulator
What do all these different versions of Artificial Intelligence (AI) mean?
There are many variations of the word AI thrown around and I just want to clarify the differences. Artificial General Intelligence (AGI) AGI is the goal of building AI systems. Humans want to build Artificial General Intelligences that can do a wide variety of tasks just like humans can do. This has been the goal… Continue reading What do all these different versions of Artificial Intelligence (AI) mean?