Sentence completion and prediction refers to the capability of filling missing words in any incomplete sentences. It is one of the keys to reading comprehension, thus making sentence completion an indispensible component of machine reading. Cogent confabulation is a bio-inspired computational model that mimics the human information processing. The building of confabulation knowledge base uses an unsupervised machine learning algorithm that extracts the relations between objects at the symbolic level. In this work, we propose performance improved training and recall algorithms that apply the cogent confabulation model to solve the sentence completion problem. Our training algorithm adopts a two-level hash table, which significantly improves the training speed, so that a large knowledge base can be built at relatively low computation cost. The proposed recall function fills missing words based on the sentence context. Experimental results show that our software can complete trained sentences with 100% accuracy. It also gives semantically correct answers to more than two thirds of the testing sentences that have not been trained before.

It is not hard to find critics of how the U.S. Congress operates today. Two of the most prominent, Thomas Mann and Norman Ornstein, have bemoaned in particular Congress's failure to follow “regular order,” which in their 2006 bookThe Broken Branchthey describe as a legislative process that incorporates “discussion, debate, negotiation, and compromise” (Mann and Ornstein 2006, 170).

We are pursuing an investigation of neuromorphic computational models and architectures in order to leverage present understanding of how the estimated 1011 neurons and 1015 neuron connections in the mammalian brain are able to do some of the things a human does, and as quickly as it does it, using slow base components, while consuming very little power on affordable synthetic non-biological computing hardware. Understanding and harvesting neurologically based methods is a promising approach with great potential that may help us achieve massively parallel computation far beyond the scope of traditional computing.

This paper describes a new approach to the problem of generating DNA tag/anti-tag libraries for use in biological assay methods. This approach couples multi-threaded coding methods and a highly parallel multi-population genetic algorithm to leverage performance gains made possible by the multicore CPUs increasingly prevalent in today's commodity computers. We also describe the results of experiments characterizing the performance of this approach, which can yield up to an 8X speedup on a workstation equipped with dual quad-core CPUs. We observe that the coding effort required to implement this approach using the C language and Pthreads parallel programming model is greatly reduced compared to previous methods using both the VHDL language and reconfigurable hardware (FPGAs), and compared to C with the MPI API run on a cluster of computers.

Cogent confabulation is a computation model that mimics the Hebbian learning, information storage, inter-relation of symbolic concepts, and the recall operations of the brain. The model has been applied to cognitive processing of language, audio and visual signals. In this project, we focus on how to accelerate the computation which underlie confabulation based sentence completion through software and hardware optimization. On the software implementation side, appropriate data structures can improve the performance of the software by more than 5,000X. On the hardware implementation side, the cogent confabulation algorithm is an ideal candidate for parallel processing and its performance can be significantly improved with the help of application specific, massively parallel computing platforms. However, as the complexity and parallelism of the hardware increases, cost also increases. Architectures with different performance-cost tradeoffs are analyzed and compared. Our analysis shows that although increasing the number of processors or the size of memories per processor can increase performance, the hardware cost and performance improvements do not always exhibit a linear relation. Hardware configuration options must be carefully evaluated in order to achieve good cost performance tradeoffs.

Reliable DNA computing requires a large pool of oligonucleotides that do not cross-hybridize. In this paper, we present a transformed algorithm to calculate the maximum weight of the 2-stem common subsequence of two DNA oligonucleotides. The result is the key part of the Gibbs free energy of the DNA cross-hybridized duplexes based on the nearest-neighbor model. The transformed algorithm preserves the physical data locality and hence is suitable for implementation using a systolic array. A novel hybrid architecture that consists of a general purpose microprocessor and a hardware accelerator for accelerating the discovery of DNA under thermodynamic constraints is designed, implemented and tested. Experimental results show that the hardware system provides more than 250X speed-up compared to a software only implementation.

In this paper, we present our work in the implementation and performance optimization of the recall operation of the brain-state-in-a-box (BSB) model on the cell broadband engine processor. We have applied optimization techniques on different parts of the algorithm to improve the overall computing and communication performance of the BSB recall algorithm. Runtime measurements show that, we have been able to achieve about 70% of the theoretical peak performance of the processor.

Research and development in modeling and simulation of human cognizance functions requires a high-performance computing platform for manipulating large-scale mathematical models. Traditional computing architectures cannot fulfill the attendant needs in terms of arithmetic computation and communication bandwidth. In this work, we propose a novel hybrid computing architecture for the simulation and evaluation of large-scale associative neural memory models. The proposed architecture achieves very high computing and communication performances by combining the technologies of hardware-accelerated computing, parallel distributed data operation and the publish/subscribe protocol. Analysis has been done on the computation and data bandwidth demands for implementing a large-scale brain-state-in-a-box (BSB) model. Compared to the traditional computing architecture, the proposed architecture can achieve at least 100X speedup.

A large and reliable DNA codeword library is the key to the success of DNA based computing. Searching for the set of reliable DNA codewords is an NP-hard problem, which can take days on the state-of-art high performance cluster computers. This work presents a hybrid architecture that consists of a general purpose microprocessor and a hardware accelerator for accelerating the discovery of DNA reverse complement, edit distance codes. Two applications of this architecture were implemented and evaluated, including a code generator that uses a genetic algorithm (GA) to produce nearly locally optimal codes in a few minutes, and a code extender that uses exhaustive search to produce locally optimum codes in about 1.5 hours for the case of length 16 codes. The experimental results demonstrate that the GA can find ~99% of the words in locally optimum libraries, and that the hybrid architecture provides more than 1000X speed-up compared to a software only implementation

A large and reliable DNA codeword library is key to the success of DNA based computing. Searching for sets of reliable DNA codewords is an NP-hard problem, which can take days on state-of-art high performance cluster computers. This work presents a hybrid architecture that consists of a general purpose microprocessor and a hardware accelerator for accelerating the multi-deme genetic algorithm (GA) for the application of DNA codeword searching. The presented architecture provides more than 1000X speed-up compared to a software only implementation. A code extender that uses exhaustive search to produce locally optimum codes in about 1.5 hours for the case of length 16 codes is also described. The experimental results demonstrate that the GA can find ~99% of the words in locally optimum libraries. Finally, we investigate the performance impact of migration, mating and mutation functions in the hardware accelerator. The analysis shows that a modified GA without mating is the most effective for DNA codeword searching.

: This report documents interim progress for an in-house project aimed at identifying, developing and evaluating applications of evolutionary computing methods to hard optimization problem test cases on a single PC computer, a cluster of computers, and hardware FPGA platforms. We surveyed evolutionary computing literature and chose to focus on the Generic Algorithm, GA. We had the GA test three case problems, Non-Linear Coupled Ordinary Differential Equation, ODE, Parameterization, the DNA Code Word Library Generation, and the Networked Senior Power Management Policy Problem. The first test problem used an ODE biomodel for Antigen-Antibody binding that was of interest to a PI for a DARPA SIMBIOSYS program we managed. We developed prototype optimization software tools in three programming environments. Labview, Matlab, and compiled C, and demonstrated speed-ups on the order of 100-1000x by moving to C. We parallelized the C codes using Message Passing interface and demonstrated good linear speed-ups on a cluster. Our GA solution for the second test case problem. DNA Code Word Library Generation, was also parallelized, and was faster than any algorithm found in the literature. Finally, we began developing a hardware accelerated version of GA for the DNA Code Word Problem as a first step toward a distributed hardware implementation.

In this work we consider energy-efficient resource management in an environment monitoring and hazard detection sensor network. Our goal is to allocate different detection methods to different sensor nodes in the way such that the required detection probability can be achieved while the network lifetime is maximized. The optimization algorithm is designed based on the Island multi-deme genetic algorithm (GA). The experimental results show that our algorithm increases the network lifetime by approximately 14.4% in average compared with the heuristic approaches. We also investigate the effect of the configuration parameters on the searching quality of the proposed distributed GA. A regression model is derived empirically that estimates the runtime of the distributed GA given the configuration parameters such as the sub-population size, parallelism, and migration rate. Once the model has been fit to a group of data, it can be utilized to find the efficient configurations of the proposed algorithm.

In this work we consider lifetime-aware resource management for sensor network using distributed genetic algorithm (GA). Our goal is to allocate different detection methods to different sensor nodes in the way such that the required detection probability can be achieved while the network lifetime is maximized. The contribution of this paper is twofold. Firstly, the resource management problem is formulated as a constraint optimization problem and is solved using a distributed GA. Secondly, empirical analysis results are provided that reveals the relationship between the configuration parameters and the quality of the search. A regression model is designed to estimate the runtime of the distributed GA given the configuration parameters. The model is utilized to find energy efficient configurations of the algorithm