We present a Bayesian deep structured semantic model (BDSSM) that is efficient in retrieval tasks with a large pool of candidates for real-time applications, e.g., in search engines and digital ads. Efficiency is achieved by indexing the items into groups based on sparse representation during offline pre-computation. In online retrieval, the algorithm only retrieves and ranks items from indices that are relevant to the query. We then explore optimization strategies in the algorithm to make sparse representations sparser. Finally, our algorithm is compared with other popular clustering-based, hashing-based, and tree-based retrieval methods. We measure the differences in multiple dimensions, including retrieval recall, storage of embeddings, and CPU time. We show that our approach outperforms other algorithms in both recall and CPU time with the same storage limit.

Despite the effort toward benchmarking self-supervised learning (SSL) methods for image recognition transfer learning tasks, our understanding is still limited about their performance on noisy real-world datasets. This paper presents an extensive analysis of various types of SSL methods on real-world datasets containing noisy images of wildlife animals. These uncurated images are auto-captured by motion-activated cameras or camera traps installed in the wild. The camera-trap datasets exhibit different types of biases typically present in practical tasks. Using a set of variably-size biased datasets, we compare the supervised learning (SL) method to two types of SSL methods, i.e., instance discrimination and cluster discrimination. Our results reveal nuances in SSL’s performance. For example, we show that though SSL methods are often more generalizable than the SL method, the performance gain of some SSL methods diminishes with the reduction in the size of the target dataset. Also, there exists significant variability in the effectiveness of the two types of SSL methods. In addition to this, we show that, unlike SL, both types of SSL gain from increased model capacity.

MOTIVATION: Empowered by advanced genomics discovery tools, recent biomedical research has produced a massive amount of genomic data on (post-)transcriptional regulations related to transcription factors, microRNAs, long non-coding RNAs, epigenetic modifications and genetic variations. Computational modeling, as an essential research method, has generated promising testable quantitative models that represent complex interplay among different gene regulatory mechanisms based on these data in many biological systems. However, given the dynamic changes of interactome in chaotic systems such as cancers, and the dramatic growth of heterogeneous data on this topic, such promise has encountered unprecedented challenges in terms of model complexity and scalability. In this study, we introduce a new integrative machine learning approach that can infer multifaceted gene regulations in cancers with a particular focus on microRNA regulation. In addition to new strategies for data integration and graphical model fusion, a supervised deep learning model was integrated to identify conditional microRNA-mRNA interactions across different cancer stages. RESULTS: In a case study of human breast cancer, we have identified distinct gene regulatory networks associated with four progressive stages. The subsequent functional analysis focusing on microRNA-mediated dysregulation across stages has revealed significant changes in major cancer hallmarks, as well as novel pathological signaling and metabolic processes, which shed light on microRNAs' regulatory roles in breast cancer progression. We believe this integrative model can be a robust and effective discovery tool to understand key regulatory characteristics in complex biological systems. AVAILABILITY: http://sbbi-panda.unl.edu/pin/.

The (inverse) discrete Fourier transform (DFT/ IDFT) is often perceived as essential to orthogonal frequency-division multiplexing (OFDM) systems. In this paper, a deep complex-valued convolutional network (DCCN) is developed to recover bits from time-domain OFDM signals without relying on any explicit DFT/IDFT. The DCCN can exploit the cyclic prefix (CP) of OFDM waveform for increased SNR by replacing DFT with a learned linear transform, and has the advantage of combining CP-exploitation, channel estimation, and intersymbol interference (ISI) mitigation, with a complexity ofO(N2). Numerical tests show that the DCCN receiver can outperform the legacy channel estimators based on ideal and approximate linear minimum mean square error (LMMSE) estimation and a conventional CP-enhanced technique in Rayleigh fading channels with various delay spreads and mobility. The proposed approach benefits from the expressive nature of complex-valued neural networks, which, however, currently lack support from popular deep learning platforms. In response, guidelines of exact and approximate implementations of a complex-valued convolutional layer are provided for the design and analysis of convolutional networks for wireless PHY. Furthermore, a suite of novel training techniques are developed to improve the convergence and generalizability of the trained model in fading channels. This work demonstrates the capability of deep neural networks in processing OFDM waveforms and the results suggest that the FFT processor in OFDM receivers can be replaced by a hardware AI accelerator.

Computational modeling of complex gene regulation among different mechanisms involving transcript factors, microRNAs, lncRNAs, epigenetic modification, in a chaotic disease system such as cancer, has posed unprecedented challenges. In this study, we introduce a new integrative framework that handles genomics data integration and network model fusion with focus on the inference of context-dependent microRNA-gene interactions. Using breast cancer as a case study, we have identified stage-specific microRNA-gene binding patterns. Functional analysis indicates microRNA regulated signaling during cancer progression.

We formalize notions of triangle and open-wedge heavy-hitters in large networks. Intuitively, a node of a network G is a triangle heavy-hitter if it participates in relatively many triangles of G (analogously for open wedges). These notions have applications in social network analysis. We consider the triangle and open-wedge heavy-hitter problems: the computational problems of maintaining a set of nodes of a network that participate in many triangles and open wedges. We give sampling-based algorithms for these problems when the input network G comes as an edge stream. We prove theoretical guarantees on the quality of solutions, time and space complexity of these algorithms. This is the first work that studies the triangle and open-wedge heavy hitters problem on massive streaming networks. We evaluate the performance of our proposed algorithms by running on several real-world data sets. These experiments indicate that our algorithms efficiently detect heavy hitters while keeping both the false-positive and the false-negative errors very low.

Many classification tasks target high-level concepts that can be decomposed into a hierarchy of finer-grained sub-concepts. For example, some string entities that are Locations are also Attractions, some Attractions are Museums, etc. Such hierarchies are common in named entity recognition (NER), document classification, and biological sequence analysis. We present a new approach for learning hierarchically decomposable concepts. The approach learns a high-level classifier (e.g., location vs. non-location) by seperately learning multiple finer-grained classifiers (e.g., museum vs. non-museum), and then combining the results. Soliciting labels at a finer level of granularity than that of the target concept is a new approach to active learning, which we term active over-labeling. In experiments in NER and document classification tasks, we show that active over-labeling substantially improves area under the precision-recall curve when compared with standard passive or active learning. Finally, because finer-grained labels may be more expensive to obtain, we also present a cost-sensitive active learner that uses a multi-armed bandit approach to dynamically choose the label granularity to target, and show that the bandit-based learner is robust to differences in label cost and labeling budget.

We study the problem of identifying reactive compound(s) in a solution as efficiently as possible, with the goal of minimizing the number of chemical tests required to make exact identification. The area of group testing is appropriate for this problem, except that most group testing approaches assume that arbitrary tests can be performed, which is not the case in our application. To address this, we introduce a new model called mask-based constrained group testing, develop a randomized algorithm for it, and prove that under the right conditions, the algorithm is guaranteed w.h.p. to efficiently identify the active compounds of a solution with a small number of tests. We also show that our algorithm performs very well empirically on synthetic and real data.

Real‐world datasets often contain large numbers of unlabeled data points, because there is additional cost for obtaining the labels. Semi‐supervised learning (SSL) algorithms use both labeled and unlabeled data points for training that can result in higher classification accuracy on these datasets. Generally, traditional SSLs tentatively label the unlabeled data points on the basis of the smoothness assumption that neighboring points should have the same label. When this assumption is violated, unlabeled points are mislabeled injecting noise into the final classifier. An alternative SSL approach is cluster‐then‐label (CTL), which partitions all the data points (labeled and unlabeled) into clusters and creates a classifier by using those clusters. CTL is based on the less restrictive cluster assumption that data points in the same cluster should have the same label. As shown, this allows CTLs to achieve higher classification accuracy on many datasets where the cluster assumption holds for the CTLs, but smoothness does not hold for the traditional SSLs. However, cluster configuration problems (e.g., irrelevant features, insufficient clusters, and incorrectly shaped clusters) could violate the cluster assumption. We propose a new framework for CTLs by using a genetic algorithm (GA) to evolve classifiers without the cluster configuration problems (e.g., the GA removes irrelevant attributes, updates number of clusters, and changes the shape of the clusters). We demonstrate that a CTL based on this framework achieves comparable or higher accuracy with both traditional SSLs and CTLs on 12 University of California, Irvine machine learning datasets.

BACKGROUND: Our environment is composed of biological components of varying magnitude. The relationships between the different biological elements can be represented as a biological network. The process of mating in S. cerevisiae is initiated by secretion of pheromone by one of the cells. Our interest lies in one particular question: how does a cell dynamically adapt the pathway to continue mating under severe environmental changes or under mutation (which might result in the loss of functionality of some proteins known to participate in the pheromone pathway). Our work attempts to answer this question. To achieve this, we first propose a model to simulate the pheromone pathway using Petri nets. Petri nets are directed graphs that can be used for describing and modeling systems characterized as concurrent, asynchronous, distributed, parallel, non-deterministic, and/or stochastic. We then analyze our Petri net-based model of the pathway to investigate the following: 1) Given the model of the pheromone response pathway, under what conditions does the cell respond positively, i.e., mate? 2) What kinds of perturbations in the cell would result in changing a negative response to a positive one? METHOD: In our model, we classify proteins into two categories: core component proteins (set ψ) and additional proteins (set λ). We randomly generate our model's parameters in repeated simulations. To simulate the pathway, we carry out three different experiments. In the experiments, we simply change the concentration of the additional proteins (λ) available to the cell. The concentration of proteins in ψ is varied consistently from 300 to 400. In Experiment 1, the range of values for λ is set to be 100 to 150. In Experiment 2, it is set to be 151 to 200. In Experiment 3, the set λ is further split into σ and ς, with the idea that proteins in σ are more important than those in ς. The range of values for σ is set to be between 151 to 200 while that of ς is 100 to 150. Decision trees were derived from each of the first two experiments to allow us to more easily analyze the conditions under which the pheromone is expressed. CONCLUSION: The simulation results reveal that a cell can overcome the detrimental effects of the conditions by using more concentration of additional proteins in λ. The first two experiments provide evidence that employing more concentration of proteins might be one of the ways that the cell uses to adapt itself in inhibiting conditions to facilitate mating. The results of the third experiment reveal that in some case the protein set σ is sufficient in regulating the response of the cell. Results of Experiments 4 and 5 reveal that there are certain conditions (parameters) in the model that are more important in determining whether a cell will respond positively or not.

Computing the minimal network of a Constraint Satisfaction Problem (CSP) is a useful and difficult task. Two algorithms, PerTuple and AllSol, were proposed to this end. The performances of these algorithms vary with the problem instance. We use Machine Learning techniques to build a classifier that predicts which of the two algorithms is likely to be more effective.

In active learning, where a learning algorithm has to purchase the labels of its training examples, it is often assumed that there is only one labeler available to label examples, and that this labeler is noise-free. In reality, it is possible that there are multiple labelers available (such as human labelers in the online annotation tool Amazon Mechanical Turk) and that each such labeler has a different cost and accuracy. We address the active learning problem with multiple labelers where each labeler has a different (known) cost and a different (unknown) accuracy. Our approach uses the idea of adjusted cost, which allows labelers with different costs and accuracies to be directly compared. This allows our algorithm to find low-cost combinations of labelers that result in high-accuracy labelings of instances. Our algorithm further reduces costs by pruning under-performing labelers from the set under consideration, and by halting the process of estimating the accuracy of the labelers as early as it can. We found that our algorithm often outperforms, and is always competitive with, other algorithms in the literature.

We report on a recently funded project called Renaissance Computing, an initiative for promoting student participation in computing. We propose a radical re-thinking not only of our core curriculum in CS, but of the role of CS at the university level. In our conception, ''computational thinking'' is neither easily separated from other endeavors nor easily balkanized into a single department. We thus imagine a CS curriculum that is inextricably linked to other domains. Our proposed initiative covers introductory, depth, and capstone courses, targeting both CS majors and minors. It is also aimed to develop interdisciplinary CS courses in sciences, engineering, arts, and humanities. Furthermore, the framework embraces collaborative learning to help improve learning.

The multiple-instance learning (MIL) model has been successful in numerous application areas. Recently, a generalization of this model and an algorithm for it were introduced, showing significant advantages over the conventional MIL model on certain application areas. Unfortunately, that algorithm is not scalable to high dimensions. We adapt that algorithm to one using a support vector machine with our new kernel k\wedge. This reduces the time complexity from exponential in the dimension to polynomial. Computing our new kernel is equivalent to counting the number of boxes in a discrete, bounded space that contain at least one point from each of two multisets. We show that this problem is #P-complete, but then give a fully polynomial randomized approximation scheme (FPRAS) for it. We then extend k\wedge by enriching its representation into a new kernel kmin, and also consider a normalized version of k\wedge that we call k\wedge/\vee (which may or may not not be a kernel, but whose approximation yielded positive semidefinite Gram matrices in practice). We then empirically evaluate all three measures on data from content-based image retrieval, biological sequence analysis, and the musk data sets. We found that our kernels performed well on all data sets relative to algorithms in the conventional MIL model.

We explore the problem of budgeted machine learning, in which the learning algorithm has free access to the training examples' labels but has to pay for each attribute that is specified. This learning model is appropriate in many areas, including medical applications. We present new algorithms for choosing which attributes to purchase of which examples in the budgeted learning model based on algorithms for the multi-armed bandit problem. All of our approaches outperformed the current state of the art. Furthermore, we present a new means for selecting an example to purchase after the attribute is selected, instead of selecting an example uniformly at random, which is typically done. Our new example selection method improved performance of all the algorithms we tested, both ours and those in the literature.

In active learning, a machine learning algorithm is given an unlabeled set of examples U, and is allowed to request labels for a relatively small subset of U to use for training. The goal is then to judiciously choose which examples in U to have labeled in order to optimize some performance criterion, e.g. classification accuracy. We study how active learning affects AUC. We examine two existing algorithms from the literature and present our own active learning algorithms designed to maximize the AUC of the hypothesis. One of our algorithms was consistently the top performer, and Closest Sampling from the literature often came in second behind it. When good posterior probability estimates were available, our heuristics were by far the best.

Active machine learning algorithms are used when large numbers of unlabeled examples are available and getting labels for them is costly (e.g. requiring consulting a human expert). Many conventional active learning algorithms focus on refining the decision boundary, at the expense of exploring new regions that the current hypothesis misclassifies. We propose a new active learning algorithm that balances such exploration with refining of the decision boundary by dynamically adjusting the probability to explore at each step. Our experimental results demonstrate improved performance on data sets that require extensive exploration while remaining competitive on data sets that do not. Our algorithm also shows significant tolerance of noise.

We present new, general-purpose kernels for protein structure analysis, and describe how to apply them to structural motif discovery and function classification. Experiments show that our new methods are faster than conventional techniques, are capable of finding structural motifs, and are very effective in function classification. In addition to strong cross-validation results, we found possible new oxidoreductases and cytochrome P450 reductases and a possible new structural motif in cytochrome P450 reductases.

We describe a generalisation of the multiple-instance learning model in which a bag's label is not based on a single instance's proximity to a single target point. Rather, a bag is positive if and only if it contains a collection of instances, each near one of a set of target points. We then adapt a learning-theoretic algorithm for learning in this model and present empirical results on data from robot vision, content-based image retrieval, and protein sequence identification.

The multiple-instance learning (MIL) model has been very successful in application areas such as drug discovery and content-based image-retrieval. Recently, a generalization of this model and an algorithm for this generalization were introduced, showing significant advantages over the conventional MIL model in certain application areas. Unfortunately, this algorithm is inherently inefficient, preventing scaling to high dimensions. We reformulate this algorithm using a kernel for a support vector machine, reducing its time complexity from exponential to polynomial. Computing the kernel is equivalent to counting the number of axis-parallel boxes in a discrete, bounded space that contain at least one point from each of two multisets P and Q. We show that this problem is #P-complete, but then give a fully polynomial randomized approximation scheme (FPRAS) for it. Finally, we empirically evaluate our kernel.

We propose a novel general piecewise surface regression model that allows for arbitrary functions to be used in each piece, and arbitrary boundary swfaces between pieces. We also give an EM-based algorithm for this model, EMPRR, that scales to high dimensions. We compare EMPRR's performance with those of model trees and functional trees, two regression tree learning methods, on synthetic piecewise data and benchmark data sets. Our results show that EMPRR outperforms the other two methods on the synthetic data sets and performs competitively on the benchmark data sets while generating accurate and compact models.

We present a support vector machine that plays strong poker based on training on data from a proven player. This approach allows us to create an agent without having to use and implement expert rules. We tested our support vector machine by having it play against several opponents. It did not perform as well as expected, but did show some promise.

Expressing web page content in a way that computers can understand is the key to a semantic web. Generating ontological information from the web automatically using machine learning shows great promise towards this goal. We present LASSO, an architecture that combines distributed components for training web page classifiers via machine learning and information extraction, and then labels new pages with the classifiers. LASSO's results are semantic models of web pages stored in a database back end, and the models are defined with respect to whatever ontology the user chooses. LASSO can be used to build a wide variety of applications or can be used as a collaborative experimentation workbench. We give as part of our proof-of-concept prototype an application of an enhanced ontological search engine. We also describe how LASSO can be used to compare machine learning algorithms and analyze our system with a code reuse metric.

The concept class of geometric patterns has been heavily studied and has applications in pattern recognition. Pr evious work on this concept class has been restricted to one or two dimensions or to finite and discretized domains. We present an algorithm to learn a very flexible generalization of previously studied geometric patterns in any constantdimensional real space, making its potential applicabilit y to pattern matching very high since it can operate on any data representable as a constant-dimensional array of values. To our knowledge, these classes of patterns are more complex than any class of geometric patterns previously studied. We also give variations of our algorithms to learn the union of constant-dimensional geometric objects from multiple-instance examples.

The multiple-instance learning (MIL) model has been successful in areas such as drug discovery and content-based image-retrieval. Recently, this model was generalized and a corresponding kernel was introduced to learn generalized MIL concepts with a support vector machine. While this kernel enjoyed empirical success, it has limitations in its representation. We extend this kernel by enriching its representation and empirically evaluate our new kernel on data from content-based image retrieval, biological sequence analysis, and drug discovery. We found that our new kernel generalized noticeably better than the old one in content-based image retrieval and biological sequence analysis and was slightly better or even with the old kernel in the other applications, showing that an SVM using this kernel does not overfit despite its richer representation.

Due to the lack of optical random access memory, optical fiber delay line (FDL) is currently the only way to implement optical buffering. Feed-forward and feedback are two kinds of FDL structures in optical buffering. Both have advantages and disadvantages. In this paper, we propose a more effective hybrid FDL architecture that combines the merits of both schemes. The core of this switch is the arrayed waveguide grating (AWG) and the tunable wavelength converter (TWC). It requires smaller optical device sizes and fewer wavelengths and has less noise than feedback architecture. At the same time, it can facilitate preemptive priority routing which feed-forward architecture cannot support. Our numerical results show that the new switch architecture significantly reduces packet loss probability.

We study an on-line problem that is motivated by the networking problem of dynamically adjusting of acknowledgments in the Transmission Control Protocol (TCP). We provide a theoretical model for this problem in which the goal is to send acks at a time that minimize a linear combination of the cost for the number of acknowledgments sent and the cost for the additional latency introduced by delaying acknowledgments. To study the usefulness of applying packet arrival time prediction to this problem, we assume there is an oracle that provides the algorithm with the times of the next L arrivals, for some L ≥ 0. We give two different objective functions for measuring the cost of a solution, each with its own measure of latency cost. For each objective function we first give an O(n 2 ) -time dynamic programming algorithm for optimally solving the off-line problem. Then we describe an on-line algorithm that greedily acknowledges exactly when the cost for an acknowledgment is less than the latency cost incurred by not acknowledging. We show that for this algorithm there is a sequence of n packet arrivals for which it is Ω (***)-competitive for the first objective function, 2-competitive for the second function for L = 0, and 1-competitivefor the second function for L = 1. Next we present a second on-line algorithm which is a slight modification of the first, and we prove that it is 2-competitive for both objective functions for all L . We also give lower bounds on the competitive ratio for any deterministic on-line algorithm. These results show that for each objective function, at least one of our algorithms is optimal. Finally, we give some initial empirical results using arrival sequences from real network traffic where we compare the two methods used in TCP for acknowledgment delay with our two on-line algorithms. In all cases we examine performance with L = 0 and L = 1.

WQ study an on-line problem that is motivated by the networking problem of dynamically adjusting delays of acknowlcdgmcnts in the Transmission Control Protocol (TCP).The thcoroticnl problem we study is the following.There is a scqucnco of n packet arrival times .4= (or,. . ., an) and a look-nhoad coefficient L, The goal is to partition A into 1; subsequences orroe,. . ., a~: (where a subsequence end is deilncd by an acknowledgment) that minimizes a linear combination of the cost for the number of acknowledgments sent and the cost for the additional latency introduced by delaylng acknowledgments.At each arrival, an oracle provides the algorithm with the times of the next L arrivals.First we give an 0(n*) dynamic programming algorithm for optimally solving the off-line problem.Then we deacribc an on-line algorithm that greedily acknowledges exactly when the cost for an acknowledgment is less than the latency cost obtained by not acknowledging.We show that for this algorithm there ls a sequence of n packet arrivals for which it is S-l (fi) -competitive.Next we present a second on-line algorithm which is a slight modification of the first that we prove is 2-competitive.Let Copt be the cost of the optimal solution and let CA be the cost of the solution produced by algorithm A. We then show that for any on-line algorithm A with any constant look-ahead L, CA > SC+-c where c is a factor that can be made arbitrarily small with rcnpcct to Capt.Thus, in the worst case, our result for L = 0 IQ the hcst possible even for on-line algorithms that can use nny constant look-ahead.We then give some initial empirical results using arrival sequences from real network traffic where we compare the two methods used in TCP for acknowledgment delay with our two on-line algorithms.In all cases we examine performance mitli L = 0 and L = 1, Finally, we consider an alternate dcilnition for the latency cost in our objective function, *Supported in part by NSF NY1 Grant CC%9357707 with mntching funds provfdcd by WUTA.

) Sally A. Goldman Dept. of Computer Science Washington University St. Louis, MO 63130-4899 [email protected] Stephen S. Kwek Dept. of Computer Science Washington University St. Louis, MO 63130-4899 [email protected] Stephen D. Scott Dept. of Computer Science Washington University St. Louis, MO 63130-4899 [email protected] Abstract We introduce the UAV learning model in which some of the attributes in the examples are unspecified. In our model, an example x is classified positive (resp., negative) if all possible assignments for the unspecified attributes result in a positive (resp., negative) classification. Otherwise the classification given to x is "?" (for unknown). Given an example x in which some attributes are unspecified, the oracle UAV-MQ responds with the classification of x. Given a hypothesis h, the oracle UAV-EQ returns an example x (that could have unspecified attributes) for which h(x) is incorrect. We show that any class learnable in the exact model using the...

Goldberg,Goldman, and Scott demonstrated how the problem of recognizing a landmark from a one-dimensional visual image can be mapped to that of learning a one-dimensional geometric pattern and gave a PAC algorithm to learn that class.We present an on-line agnostic learning algorithm for learning the class of one-dimensional geometric patterns.Since, when moving from the processed visual image to a one-dimensional pattern some key information is lost, we define a class of two-dimensional geometric patterns for which the important features from the visual image are incorporated in the geometric pattern, and show how to extend our agnostic learning algorithm to this class of two-dimensional patterns.Prnllissiofl lo InnLc digltnl!l~nrd copies ofall or p;m ofllli\ tll;~ir'r~i~l lb, penonnl or cl~wsroom wsc is ~I-mli'd w~tlwut I>c prob &d th;~r 111~ cop<\ arc IMM made or distribukd IOr profit or commcrc~~~l .~tl\x~lt;~gc.tile copyrlglit nolice.Ihe liilc oflhc pul~lic;llio~l and iLv J;kIc ;nppc;kr.:III~ llollcc jl: giwn that copyrighl is hy pmn~~on ofthe ,\c'kl.IIK '1'0 copy OLIIC~W~?.~'. 10 rrpuhlirh.10 posl 01) wvm or lo rtxilstrihulc IO 11~15.rqutrcs hpcClliC pemlission and/or Ibe ( 'OL.7' 97 Naslnille.Tcnncsec.USA Copyright I997 i\Ckl O-R9791 -89 I -(v97'7..$? 50

A genetic algorithm (GA) is a robust problem-solving method based on natural selection. Hardware's speed advantage and its ability to parallelize offer great rewards to genetic algorithms. Speedups of 1-3 orders of magnitude have been observed when frequently used software routines were implemented in hardware by way of reprogrammable field-programmable gate arrays (FPGAs). Reprogrammability is essential in a general-purpose GA engine because certain GA modules require changeability (e.g. the function to be optimized by the GA). Thus a hardware-based GA is both feasible and desirable. A fully functional hardware-based genetic algorithm (the HGA) is presented here as a proof-of-concept system. It was designed using VHDL to allow for easy scalability. It is designed to act as a coprocessor with the CPU of a PC. The user programs the FPGAs which implement the function to be optimized. Other GA parameters may also be specified by the user. Simulation results and performance analyses of the HGA are presented. A prototype HGA is described and compared to a similar GA implemented in software. In the simple tests, the prototype took about 6% as many clock cycles to run as the software-based GA. Further suggested improvements could realistically make the HGA 2–3 orders of magnitude faster than the software-based GA.