Date of Award
Doctor of Philosophy (PhD)
Electrical Engineering and Computer Science
The advancements in high performance computing (HPC) have enabled the large-scale implementation of neuromorphic learning models and pushed the research on computational intelligence into a new era. Those bio-inspired models are constructed on top of unified building blocks, i.e. neurons, and have revealed potentials for learning of complex information. Two major challenges remain in neuromorphic computing. Firstly, sophisticated structuring methods are needed to determine the connectivity of the neurons in order to model various problems accurately. Secondly, the models need to adapt to non-traditional architectures for improved computation speed and energy efficiency. In this thesis, we address these two problems and apply our techniques to different cognitive applications.
This thesis first presents the self-structured confabulation network for anomaly detection. Among the machine learning applications, unsupervised detection of the anomalous streams is especially challenging because it requires both detection accuracy and real-time performance. Designing a computing framework that harnesses the growing computing power of the multicore systems while maintaining high sensitivity and specificity to the anomalies is an urgent research need. We present AnRAD (Anomaly Recognition And Detection), a bio-inspired detection framework that performs probabilistic inferences. We leverage the mutual information between the features and develop a self-structuring procedure that learns a succinct confabulation network from the unlabeled data. This network is capable of fast incremental learning, which continuously refines the knowledge base from the data streams. Compared to several existing anomaly detection methods, the proposed approach provides competitive detection accuracy as well as the insight to reason the decision making. Furthermore, we exploit the massive parallel structure of the AnRAD framework. Our implementation of the recall algorithms on the graphic processing unit (GPU) and the Xeon Phi co-processor both obtain substantial speedups over the sequential implementation on general-purpose microprocessor (GPP). The implementation enables real-time service to concurrent data streams with diversified contexts, and can be applied to large problems with multiple local patterns. Experimental results demonstrate high computing performance and memory efficiency. For vehicle abnormal behavior detection, the framework is able to monitor up to 16000 vehicles and their interactions in real-time with a single commodity co-processor, and uses less than 0.2ms for each testing subject.
While adapting our streaming anomaly detection model to mobile devices or unmanned systems, the key challenge is to deliver required performance under the stringent power constraint. To address the paradox between performance and power consumption, brain-inspired hardware, such as the IBM Neurosynaptic System, has been developed to enable low power implementation of neural models. As a follow-up to the AnRAD framework, we proposed to port the detection network to the TrueNorth architecture. Implementing inference based anomaly detection on a neurosynaptic processor is not straightforward due to hardware limitations. A design flow and the supporting component library are developed to flexibly map the learned detection networks to the neurosynaptic cores. Instead of the popular rate code, burst code is adopted in the design, which represents numerical value using the phase of a burst of spike trains. This does not only reduce the hardware complexity, but also increases the result's accuracy. A Corelet library, NeoInfer-TN, is implemented for basic operations in burst code and two-phase pipelines are constructed based on the library components. The design can be configured for different tradeoffs between detection accuracy, hardware resource consumptions, throughput and energy. We evaluate the system using network intrusion detection data streams. The results show higher detection rate than some conventional approaches and real-time performance, with only 50mW power consumption. Overall, it achieves 10^8 operations per Joule.
In addition to the modeling and implementation of unsupervised anomaly detection, we also investigate a supervised learning model based on neural networks and deep fragment embedding and apply it to text-image retrieval. The study aims at bridging the gap between image and natural language. It continues to improve the bidirectional retrieval performance across the modalities. Unlike existing works that target at single sentence densely describing the image objects, we elevate the topic to associating deep image representations with noisy texts that are only loosely correlated. Based on text-image fragment embedding, our model employs a sequential configuration, connects two embedding stages together. The first stage learns the relevancy of the text fragments, and the second stage uses the filtered output from the first one to improve the matching results. The model also integrates multiple convolutional neural networks (CNN) to construct the image fragments, in which rich context information such as human faces can be extracted to increase the alignment accuracy. The proposed method is evaluated with both synthetic dataset and real-world dataset collected from picture news website. The results show up to 50% ranking performance improvement over the comparison models.
Chen, Qiuwen, "Neuromorphic Learning Systems for Supervised and Unsupervised Applications" (2016). Dissertations - ALL. 567.