Structured Multi-Hashing for Model Compression. (arXiv:1911.11177v1 [cs.LG])

Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory. Model compression methods address this limitation by reducing the memory footprint, latency, or energy consumption of a model with minimal impact on accuracy. We focus…

Bivariate, Cluster and Suitability Analysis of NoSQL Solutions for Different Application Areas. (arXiv:1911.11181v1 [cs.DB])

Big data systems development is full of challenges in view of the variety of application areas and domains that this technology promises to serve. Typically, fundamental design decisions involved in big data systems design include choosing appropriate storage and computing infrastructures. In this age of heterogeneous systems that integrate different technologies for development of an…

Managing Variability in Relational Databases by VDBMS. (arXiv:1911.11184v1 [cs.DB])

Variability inherently exists in databases in various contexts which creates database variants. For example, variants of a database could have different schemas/content (database evolution problem), variants of a database could root from different sources (data integration problem), variants of a database could be deployed differently for specific application domain (deploying a database for different configurations…

Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning. (arXiv:1911.11185v1 [cs.LG])

Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed with two basic yet general theories for transfer learning: (i) a task shares a common abstract structure that is invariant across domains,…

Orienting Ordered Scaffolds: Complexity and Algorithms. (arXiv:1911.11190v1 [q-bio.GN])

Despite the recent progress in genome sequencing and assembly, many of the currently available assembled genomes come in a draft form. Such draft genomes consist of a large number of genomic fragments (scaffolds), whose order and/or orientation (i.e., strand) in the genome are unknown. There exist various scaffold assembly methods, which attempt to determine the…

A Novel Unsupervised Post-Processing Calibration Method for DNNS with Robustness to Domain Shift. (arXiv:1911.11195v1 [cs.LG])

The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent. Many calibration methods in the literature have been proposed to improve the predictive uncertainty of DNNs which are generally not well-calibrated. However, none of them is specifically designed to work properly under domain…

Machine-learned metrics for predicting thelikelihood of success in materials discovery. (arXiv:1911.11201v1 [cond-mat.mtrl-sci])

Materials discovery is often compared to the challenge of finding a needle in a haystack. While much work has focused on accurately predicting the properties of candidate materials with machine learning (ML), which amounts to evaluating whether a given candidate is a piece of straw or a needle, less attention has been paid to a…

Energy-efficient stochastic computing with superparamagnetic tunnel junctions. (arXiv:1911.11204v1 [cs.ET])

Superparamagnetic tunnel junctions have emerged as a competitive, realistic nanotechnology to support novel forms of stochastic computation in CMOS-compatible platforms. One of their applications is to generate random bitstreams suitable for use in stochastic computing implementations. We describe a method for digitally programmable bitstream generation based on pre-charge sense amplifiers which is more energy efficient…