An ANN will need to be able to distinguish between four different colors based on the shape, such a circle.
This is the starting point for a radically different approach to computation, known as hyperdimensional computing.
For this purpose, he has invented a new type of vector, or hypervector.
A hyperdimensional vector is an array of ten thousand numbers, say, representing a point in 10,000 dimensions space.
In this case, the dimensions are those of infinite space.
According to him, this promises a new world in which computing is efficient and robust and machine-made decisions are entirely transparent.
Next, we need to understand the relationships between the shapes’ color and their values.
He uses four different neural nets to control this task.
👋 Feeling the vibes?
Keep the good energy going by checking out my Amazon affiliate link for some cool finds! 🛍️
If not, consider contributing to my caffeine supply at Buy Me a Coffee ☕️.
Your clicks = cosmic support for more awesome content! 🚀🌈
Leave a Reply