Engineering Commons^™

Sparse Coding On Stereo Video For Object Detection, Sheng Y. Lundquist, Melanie Mitchell, Garrett T. Kenyon

Computer Science Faculty Publications and Presentations

Deep Convolutional Neural Networks (DCNN) require millions of labeled training examples for image classification and object detection tasks, which restrict these models to domains where such a dataset is available. We explore the use of unsupervised sparse coding applied to stereo-video data to help alleviate the need for large amounts of labeled data. In this paper, we show that unsupervised sparse coding is able to learn disparity and motion sensitive basis functions when exposed to unlabeled stereo-video data. Additionally, we show that a DCNN that incorporates unsupervised learning exhibits better performance than fully supervised networks. Furthermore, finding a sparse representation …

A Theory Of Name Resolution, Pierre Néron, Andrew Tolmach, Eelco Visser, Guido Wachsmuth

Computer Science Faculty Publications and Presentations

We describe a language-independent theory for name binding and resolution, suitable for programming languages with complex scoping rules including both lexical scoping and modules. We formulate name resolution as a two-stage problem. First a language-independent scope graph is constructed using language-specific rules from an abstract syntax tree. Then references in the scope graph are resolved to corresponding declarations using a language-independent resolution process. We introduce a resolution calculus as a concise, declarative, and language- independent specification of name resolution. We develop a resolution algorithm that is sound and complete with respect to the calculus. Based on the resolution calculus we …

Resizable, Scalable, Concurrent Hash Tables, Josh Triplett, Paul E. Mckenney, Jonathan Walpole

Computer Science Faculty Publications and Presentations

We present algorithms for shrinking and expanding a hash table while allowing concurrent, wait-free, linearly scalable lookups. These resize algorithms allow the hash table to maintain constant-time performance as the number of entries grows, and reclaim memory as the number of entries decreases, without delaying or disrupting readers.

We implemented our algorithms in the Linux kernel, to test their performance and scalability. Benchmarks show lookup scalability improved 125x over readerwriter locking, and 56% over the current state-of-the-art for Linux, with no performance degradation for lookups during a resize.

To achieve this performance, this hash table implementation uses a new concurrent …

Dynamic Load Distribution In Mist, K. Al-Saqabi, R. M. Prouty, Dylan Mcnamee, Steve Otto, Jonathan Walpole

Computer Science Faculty Publications and Presentations

This paper presents an algorithm for scheduling parallel applications in large-scale, multiuser, heterogeneous distributed systems. The approach is primarily targeted at systems that harvest idle cycles in general-purpose workstation networks, but is also applicable to clustered computer systems and massively parallel processors. The algorithm handles unequal processor capacities, multiple architecture types and dynamic variations in the number of processes and available processors. Scheduling decisions are driven by the desire to minimize turnaround time while maintaining fairness among competing applications. For efficiency, the virtual processors (VPs) of each application are gang scheduled on some subset of the available physical processors.