Autonomous Learning with High-Dimensional Computing Architecture Similar to von Neumann's
This work addresses the challenge of understanding brain computation for researchers in AI and neuroscience, but it is incremental as it builds on existing ideas from psychology and biology without presenting new experimental results.
The paper tackles the problem of modeling human and animal learning by proposing a high-dimensional computing architecture using vectors (e.g., H=10,000) that resembles von Neumann computing but operates on vectors in superposition, with applications to robotics and language. The result is a theoretical framework that integrates psychology, biology, and computing, aiming to achieve brain-like efficiency in material and energy use.
We model human and animal learning by computing with high-dimensional vectors (H = 10,000 for example). The architecture resembles traditional (von Neumann) computing with numbers, but the instructions refer to vectors and operate on them in superposition. The architecture includes a high-capacity memory for vectors, analogue of the random-access memory (RAM) for numbers. The model's ability to learn from data reminds us of deep learning, but with an architecture closer to biology. The architecture agrees with an idea from psychology that human memory and learning involve a short-term working memory and a long-term data store. Neuroscience provides us with a model of the long-term memory, namely, the cortex of the cerebellum. With roots in psychology, biology, and traditional computing, a theory of computing with vectors can help us understand how brains compute. Application to learning by robots seems inevitable, but there is likely to be more, including language. Ultimately we want to compute with no more material and energy than used by brains. To that end, we need a mathematical theory that agrees with psychology and biology, and is suitable for nanotechnology. We also need to exercise the theory in large-scale experiments. Computing with vectors is described here in terms familiar to us from traditional computing with numbers.