Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design.

In resource-constrained environments, such as low-power edge devices and smart sensors, deploying a fast, compact, and accurate intelligent system with minimum energy is indispensable. Embedding intelligence can be achieved using neural networks on neuromorphic hardware. Designing such networks would require determining several inherent hyperparameters. A key challenge is to find the optimum set of hyperparameters that might belong to the input/output encoding modules, the neural network itself, the application, or the underlying hardware. In this work, we present a hierarchical pseudo agent-based multi-objective Bayesian hyperparameter optimization framework (both software and hardware) that not only maximizes the performance of the network, but also minimizes the energy and area requirements of the corresponding neuromorphic hardware. We validate performance of our approach (in terms of accuracy and computation speed) on several control and classification applications on digital and mixed-signal (memristor-based) neural accelerators. We show that the optimum set of hyperparameters might drastically improve the performance of one application (i.e., 52-71% for Pole-Balance), while having minimum effect on another (i.e., 50-53% for RoboNav). In addition, we demonstrate resiliency of different input/output encoding, training neural network, or the underlying accelerator modules in a neuromorphic system to the changes of the hyperparameters.

Characterizing mammography reports for health analytics.

As massive collections of digital health data are becoming available, the opportunities for large-scale automated analysis increase. In particular, the widespread collection of detailed health information is expected to help realize a vision of evidence-based public health and patient-centric health care. Within such a framework for large scale health analytics we describe the transformation of a large data set of mostly unlabeled and free-text mammography data into a searchable and accessible collection, usable for analytics. We also describe several methods to characterize and analyze the data, including their temporal aspects, using information retrieval, supervised learning, and classical statistical techniques. We present experimental results that demonstrate the validity and usefulness of the approach, since the results are consistent with the known features of the data, provide novel insights about it, and can be used in specific applications. Additionally, based on the process of going from raw data to results from analysis, we present the architecture of a generic system for health analytics from clinical notes.