Cleanup Memory in Biologically Plausible Neural Networks

I hereby declare that I am the sole author of this thesis. This is a true copy of the thesis, including any required final revisions, as accepted by my examiners. I understand that my thesis may be made electronically available to the public. ii During the past decade, a new class of knowledge representation has emerged known as structured distributed representation (SDR). A number of schemes for encoding and manipulating such representations have been developed; e.g. Pol-lack’s Recursive Auto-Associative Memory (RAAM), Kanerva’s Binary Spatter Code (BSC), Gayler’s MAP encoding, and Plate’s Holographically Reduced Rep-resentations (HRR). All such schemes encode structural information throughout the elements of high dimensional vectors, and are manipulated with rudimentary algebraic operations. Most SDRs are very compact; components and compositions of components are all represented as fixed-width vectors. However, such compact compositions are unavoidably noisy. As a result, resolving constituent components requires a cleanup memory. In its simplest form, cleanup is performed with a list of vectors that are sequentially compared using a similarity metric. The closest match is deemed the cleaned codevector. While SDR schemes were originally designed to perform cognitive tasks, none of them have been demonstrated in a neurobiologically plausible substrate. Po-tentially, mathematically proven properties of these systems may not be neurally realistic. Using Eliasmith and Anderson’s 2003 Neural Engineering Framework, I construct various spiking neural networks to simulate a general cleanup memory that is suitable for many schemes. Importantly, previous work has not taken advantage of parallelization or the high-dimensional properties of neural networks. Nor have they considered the ef-iii fect of noise within these systems. As well, additional improvements to the cleanup operation may be possible by more efficiently structuring the memory itself. In this thesis I address these lacuna, provide an analysis of systems accuracy, capac-ity, scalability, and robustness to noise, and explore ways to improve the search efficiency. i