Computing is entering an era of hundreds to thousands of processing elements per chip, yet no known parallelism form scales to that degree. To address this problem, we investigate the foundation of a computer architecture where processing elements and memory are contextually partitioned based upon facets of a user's life. Such Contextual Partitioning (CP), the situational handling of inputs, employs a method for allocating resources, novel from approaches used in today's architectures. Instead of focusing components on mutually exclusive parts of a task, as in Thread Level Parallelism, CP assigns different physical components to different versions of the same task, defining versions by contextual distinctions in device usage. Thus, application data is processed differently based on the situation of the user. Further, partitions may be user specific, leading to personalized architectures. Our focus is mobile devices, which are, or can be, personalized to one owner. Our investigation is centered on leveraging CP for accurate and real-time speech recognition on mobile devices, scalable to large vocabularies, a highly desired application for future user interfaces. By contextually partitioning a vocabulary, training partitions as separate acoustic models with SPHINX, we demonstrate a maximum error reduction of 61% compared to a unified approach. CP also allows for systems robust to changes in vocabulary, requiring up to 97% less training when updating old vocabulary entries with new words, and incurring fewer errors from the replacement. Finally, CP has the potential to scale nearly linearly with increasing core counts, offering architectures effective with future processor designs. / Master of Science

Understanding the brain and its functions is achallenging undertaking. To facilitate this work, brain-inspiredtechnology may be used to examine cognitive phenomena to acertain extent, by replacing real biological brains with simulations.The aim of this project was to provide insights intohow different kinds of plasticity modulation affected long-termmemory recall through the use of a computational model. Aneural network was constructed based on the existing BayesianConfidence Propagation Neural Network (BCPNN) model andtrained with binary patterns representing memories acquiredover a lifetime. By varying network plasticity parameters forselected patterns and performing recall of “aging” memories,greater effects were observed in recall statistics for modulationearly in the lifetime in comparison with modulation of later ages.From the experiments conducted in this study it was possible toconclude that selective modulation of learning affected the longtermrecall of all memories in the simulation. / Att förstå hjärnan och alla dess funktionerär en stor utmaning. För att underlätta detta arbete kanhjärninspirerad teknologi i viss utsträckning användas för attstudera kognitiva fenomen, genom att ersätta biologiska hjärnormed simuleringar. Syftet med denna studie var att ge en insikt ihur olika typer av modulering av synaptisk plasticitet påverkadeett simulerat biologiskt långtidsminne genom användning av endatoriserad modell. Ett neuralt nätverk implementerat med eninlärningsregel av typen Bayesian Confidence Propagation NeuralNetwork (BCPNN) konstruerades och användes för att träna och återkalla binära mönster, representerande minnen förvärvadeunder en livstid. Nätverkets synaptiska plasticitet varierades underträning av utvalda mönster och därefter utfördes återkallningav “åldrade” minnen. Testerna påvisade effekt på nätverketsförmåga att korrekt återkalla lagrade minnen. Det visade sigäven att modulering utförd på tidiga simulerade åldrar jämförtmed modulering av senare åldrar under livstiden hade störrepåverkan på långtidsminnet. Från resultaten var det möjligtatt konstatera att selektiv plasticitetsmodulering under inlärningpåverkade nätverkets förmåga att korrekt återkalla samtligabinära mönster i simuleringen. / Kandidatexjobb i elektroteknik 2021, KTH, Stockholm