Cognitive Signal Processing: The Ersatz Brain Project

We want to design a suitable computer for the efficient execution of the software now being developed that will display human-like cognitive abilities. One possible application is to signal processing in complex environments where some biologically and cognitively based techniques could be used for information integration and sensor fusion. The overall design is based on ideas taken from the anatomy of mammalian neocortex. In common with some other such attempts it is a massively parallel, two-dimensional array of CPUs and their associated memory. However, the design used in this project (1) uses an approximation to cortical computation called the network of networks which holds that the basic computing unit in the cortex is not a single neuron but small groups of them working together in attractor networks; and (2) assumes connections in cortex are sparse. The resulting architecture depends largely on local data movement. The sensor fusion model uses lateral data transfer to (1) spatialize important aspects of the input data, including relationships among features, and (2) potentially extract hierarchical structure in the data if it exists