#llm #ai #humans #reference-frames Created at 080423 # [Anonymous feedback](https://www.admonymous.co/louis030195) # [[Epistemic status]] #shower-thought Last modified date: 080423 Commit: 0 # Related - [[Biology/Neuroscience/Reference frame]] - [[Computing/Embeddings in the human mind]] - [[Computing/Intelligence/Machine Learning/Geometric deep learning/Geometric deep learning]] - [[Readwise/Articles/mass media - Framing (Social Sciences) - Wikipedia]] - [[Computing/Intelligence/Machine Learning/Embedding is the dark matter of intelligence]] - [[Templates/Core/Epistemic]] # Embedding in the human mind are reference frames [[Reference frame]] is an idea from [[Jeff Hawkins - A Thousand Brains_ A New Theory of Intelligence|Jeff Hawkins]] who is a neuroscientist and entrepreneur who is known for his work on artificial intelligence and brain research. In his book, "A Thousand Brains: A New Theory of Intelligence," Hawkins introduces the concept of reference frames as a key principle in understanding how the brain processes information. A reference frame is a way of representing the position and orientation of objects in relation to one another. It is a set of coordinates that allows us to locate an object in space and understand its position relative to other objects. Hawkins argues that reference frames are a fundamental idea in how the brain makes sense of the world around us. According to Hawkins, the brain creates multiple different reference frames to represent different aspects of the environment. For example, we might have a reference frame for the location of objects in our immediate surroundings, another for the location of objects in our visual field, and another for the location of objects in relation to our body. These different reference frames allow the brain to integrate information from different senses and make sense of complex environments. They also allow us to perform tasks like navigation, object recognition, and spatial reasoning. Overall, the concept of reference frames is a key idea in Hawkins' theory of intelligence and has important implications for understanding how the brain processes information and creates our perception of the world. In [[Machine learning]], [[Embeddings|embedding]] allow you to create a numerical representation on data, that can be used to compare similarity. Embeddings are related to reference frames in the sense that they both involve creating a representation of objects in a multi-dimensional space. However, while reference frames are a fundamental aspect of the human brain's processing of information, embeddings is the bridge between modalities and organs of [[Artificial intelligence|artificial intelligence]].