Brain inspired Hyperdimensional computing for extremely robust brain-computer interfaces, biosignal processing and robotics

From an engineering perspective, computing is the systematized and mechanized manipulation of patterns.  A representation is a pattern in some physical medium, for example, the configuration of ONs and OFFs on a set of switches. The algorithm then tells us how to change these patterns—how to set the switches from one moment to the next based on their previous settings. Computing is the transformation of representations by algorithms that can be described by rules.

Modern computer architecture, known as the von Neumann architecture, is a mere 60 years old. It is based on the simple idea that data and the instructions for manipulating the data are entities of the same kind. Both can be processed and stored as data in a singe uniform memory. The phenomenal success of this architecture has made computers an ubiquitous part of our lives. However, to build computers that work at all like brains, likely requires brainlike architecture .

The brain’s circuits are massive in terms of numbers of neurons and synapses, suggesting that large circuits are fundamental to the brain’s computing.  Computing with 10,000-bit words takes us into the realm of very high-dimensional spaces and vectors; we will call them hyperdimensional when the dimensionality is in the thousands. and we will use hyperspace as shorthand for hyperdimensional space, and similarly hypervector.

The way the brain works suggests that rather than working with numbers that we are used to, computing with high-dimensional (HD) vectors, e.g., 10,000 bits is more efficient. Computing with HD vectors, referred to as “hypervectors,” offers a general and scalable model of computing as well as well-defined set of arithmetic operations that can enable fast and one-shot learning (no need of back-propagation like in neural networks).

They represent things in highdimensional vectors that are manipulated by operations that produce new high-dimensional vectors in the style of traditional computing, in what is called here hyperdimensional computing on account of the very high dimensionality.