Theses and Dissertations from UMD
Permanent URI for this communityhttp://hdl.handle.net/1903/2
New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
2 results
Search Results
Item Efficient Machine Learning Techniques for Neural Decoding Systems(2022) wu, xiaomin; Bhattacharyya, Shuvra S.; Chen, Rong; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In this thesis, we explore efficient machine learning techniques for calcium imaging based neural decoding in two directions: first, techniques for pruning neural network models to reduce computational complexity and memory cost while retaining high accuracy; second, new techniques for converting graph-based input into low-dimensional vector form, which can be processed more efficiently by conventional neural network models. Neural decoding is an important step in connecting brain activity to behavior --- e.g., to predict movement based on acquired neural signals. Important application areas for neural decoding include brain-machine interfaces and neuromodulation. For application areas such as these, real-time processing of neural signals is important as well as high quality information extraction from the signals. Calcium imaging is a modality that is of increasing interest for studying brain activity. Miniature calcium imaging is a neuroimaging modality that can observe cells in behaving animals with high spatial and temporalresolution, and with the capability to provide chronic imaging. Compared to alternative modalities, calcium imaging has potential to enable improved neural decoding accuracy. However, processing calcium images in real-time is a challenging task as it involves multiple time-consuming stages: neuron detection, motion correction, and signal extraction. Traditional neural decoding methods, such as those based on Wiener and Kalman filters, are fast; however, they are outperformed in terms of accuracy by recently-developed deep neural network (DNN) models. While DNNs provide improved accuracy, they involve high computational complexity, which exacerbates the challenge of real-time processing. Addressing the challenges of high-accuracy, real-time, DNN-based neural decoding is the central objective of this research. As a first step in addressing these challenges, we have developed the NeuroGRS system. NeuroGRS is designed to explore design spaces for compact DNN models and optimize the computational complexity of the models subject to accuracy constraints. GRS, which stands for Greedy inter-layer order with Random Selection of intra-layer units, is an algorithm that we have developed for deriving compact DNN structures. We have demonstrated the effectiveness of GRS to transform DNN models into more compact forms that significantly reduce processing and storage complexity while retaining high accuracy. While NeuroGRS provides useful new capabilities for deriving compact DNN models subject to accuracy constraints, the approach has a significant limitation in the context of neural decoding. This limitation is its lack of scalability to large DNNs. Large DNNs arise naturally in neural decoding applications when the brain model under investigation involves a large number of neurons. As the size of the input DNN increases, NeuroGRS becomes prohibitively expensive in terms of computationaltime. To address this limitation, we have performed a detailed experimental analysis of how pruned solutions evolve as GRS operates, and we have used insights from this analysis to develop a new DNN pruning algorithm called Jump GRS (JGRS). JGRS maintains similar levels of model quality --- in terms of predictive accuracy --- as GRS while operating much more efficiently and being able to handle much larger DNNs under reasonable amounts of time and reasonable computational resources. Jump GRS incorporates a mechanism that bypasses (``jumps over'') validation and retraining during carefully-selected iterations of the pruning process. We demonstrate the advantages and improved scalability of JGRS compared to GRS through extensive experiments in the context of DNNs for neural decoding. We have also developed methods for raising the level of abstraction in the signal representation used for calcium imaging analysis. As a central part of this work, we invented the WGEVIA (Weighted Graph Embedding with Vertex Identity Awareness) algorithm, which enables DNN-based processing of neuron activity that is represented in the form of microcircuits. In contrast to traditional representations of neural signals, which involve spiking signals, a microcircuit representation is a graphical representation. Each vertex in a microcircuit corresponds to a neuron, and each edge carries a weight that captures information about firing relationships between the neurons associated with the vertices that are incident to the edge. Our experiments demonstrate that WGEVIA is effective at extracting information from microcircuits. Moreover,raising the level of abstraction to microcircuit analysis has the potential to enable more powerful signal extraction under limited processing time and resources.Item Spatiotemporal Dynamics and Functional Organization of Auditory Cortex Networks(2021) Bowen, Zac; Kanold, Patrick O; Losert, Wolfgang; Biophysics (BIPH); Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The sensory cortices of the brain are highly complex systems that are uniquely adapted to reliably process any encountered sensory stimulus. Sensory stimuli such as sound are encoded in large populations of neurons that exhibit some functional organization in the cortex. For example, the auditory cortex has a characteristic organization of sound frequency by which neuronal responses are organized. However, this organization is a broad approximation of more complex and diverse functional properties of individual neurons. Furthermore, on a finer temporal scale, the moment-to-moment activity dynamics of populations of neurons are incredibly complex. Numerous studies have shown that spatiotemporal cascades of co-active neurons organize as neuronal avalanches possessing certain characteristics such as size, duration, and shape that fit the parameters of a critical system. Nevertheless, it remains that the exact manner in which neuronal populations encode information is still not fully understood. This dissertation makes use of neuroimaging data acquired with 2-photon calcium imaging of the auditory cortex in awake mice to investigate the spatiotemporal and functional organization of active neuronal populations in auditory cortex at a range of temporal and spatial scales. I aimed to gain a deeper understanding into how neuronal population dynamics and the underlying network organization contribute to sound encoding in auditory cortex. I studied input and associative layers of auditory cortex (L4 and L2/3) in a mouse model with normal hearing and another with age-related hearing loss due to loss of proper cochlear function to high-frequency sound. L4 and L2/3 contained populations of neurons with a large diversity in functional properties, though diversity was reduced in the hearing loss model due to paucity of high frequency tuned neurons. Despite the diverse tuning in both, similarly responding neurons tended to be co-localized in cortical space. I found that this result extended to volumetric samples of L2/3 where large populations of neurons contained a functional network architecture indicative of small-world topology. Furthermore, I demonstrated that L4 and L2/3 contain ensembles of co-active neurons indicative of critical dynamics in both the absence and presence of a stimulus. Finally, I developed software that facilitates real-time quantification of neuronal populations during an experiment which opens the door for novel closed-loop experiment design. This dissertation provides several avenues for further investigation into neuronal population coding and dynamics, functional network topology, and provides the groundwork for closed-loop experimental design.