Sung-Soon Choi

Stock prediction based on financial correlation

In this paper, we propose a neuro-genetic stock prediction system based on financial correlation between companies. A number of input variables are produced from the relatively highly correlated companies. The genetic algorithm selects a set of informative input features among them for a recurrent neural network. It showed notable improvement over not only the buy-and-hold strategy but also the recurrent neural network using only the input variables from the target company.

An evolutionary keystroke authentication based on ellipsoidal hypothesis space

Keystroke authentication is a biometric method utilizing the typing characteristics of users. In this paper, we propose an evolutionary method for stable keystroke authentication. In the method, typing characteristics of users are represented by n-dimensional vectors and an ellipsoidal hypothesis space, which distinguishes a collection of the timing vectors of a user from those of the others, is evolved by a genetic algorithm. A filtering scheme and an adaptation mechanism are also presented to improve the stability and effectiveness of the proposed method. Empirical results show that the error rates of our method for authentication are reasonably small.

A graph-based Lamarckian-Baldwinian hybrid for the sorting network problem

A hybrid genetic algorithm (GA) is proposed for the optimal sorting network problem. Based on a graph-theoretical viewpoint, we devised a solution repair heuristic which incorporates a strong local optimization. We also propose a new encoding scheme which combines the characteristics of Lamarckian and Baldwinian GAs. Using a single-CPU PC, we obtained results comparable to previous results obtained with supercomputers.

Normalization for Genetic Algorithms With Nonsynonymously Redundant Encodings

Normalization transforms one parent genotype to be consistent with the other before crossover. In this paper, we explain how normalization alleviates the difficulties caused by nonsynonymously redundant encodings in genetic algorithms. We define the encodings with maximally nonsynonymous property and prove that the encodings induce uncorrelated search spaces. Extensive experiments for a number of problems show that normalization transforms the uncorrelated search spaces to correlated ones and leads to significant improvement in performance.

Almost tight upper bound for finding Fourier coefficients of bounded pseudo-Boolean functions

A k-bounded pseudo-Boolean function is a real-valued function on {0,1}^n that can be expressed as a sum of functions depending on at most k input bits. The k-bounded functions play an important role in a number of areas including molecular biology, biophysics, and evolutionary computation. We consider the problem of finding the Fourier coefficients of k-bounded functions, or equivalently, finding the coefficients of multilinear polynomials on {-1,1}^n of degree k or less. Given a k-bounded function f with m non-zero Fourier coefficients for constant k, we present a randomized algorithm to find the Fourier coefficients of f with high probability in O(mlogn) function evaluations. The best known upper bound was O(@l(n,m)mlogn), where @l(n,m) is between n^1^2 and n depending on m. Our bound improves the previous bound by a factor of @W(n^1^2). It is almost tight with respect to the lower bound @W(mlognlogm). In the process, we also consider the problem of finding k-bounded hypergraphs with a certain type of queries under an oracle with one-sided error. The problem is of self interest and we give an optimal algorithm for the problem.

Lower and Upper Bounds for Linkage Discovery

For a real-valued function f defined on {0,1}n , the linkage graph of f is a hypergraph that represents the interactions among the input variables with respect to f . In this paper, lower and upper bounds for the number of function evaluations required to discover the linkage graph are rigorously analyzed in the black box scenario. First, a lower bound for discovering linkage graph is presented. To the best of our knowledge, this is the first result on the lower bound for linkage discovery. The investigation on the lower bound is based on Yaos minimax principle. For the upper bounds, a simple randomized algorithm for linkage discovery is analyzed. Based on the Kruskal-Katona theorem, we present an upper bound for discovering the linkage graph. As a corollary, we rigorously prove that O(n 2logn) function evaluations are enough for bounded functions when the number of hyperedges is O(n), which was suggested but not proven in previous works. To see the typical behavior of the algorithm for linkage discovery, three random models of fitness functions are considered. Using probabilistic methods, we prove that the number of function evaluations on the random models is generally smaller than the bound for the arbitrary case. Finally, from the relation between the linkage graph and the Walsh coefficients, it is shown that, for bounded functions, the proposed bounds are eventually the bounds for finding the Walsh coefficients.

Properties of Symmetric Fitness Functions

The properties of symmetric fitness functions are investigated. We show that the search spaces obtained from symmetric functions have the zero-correlation structures between fitness and distance. It is also proven that symmetric functions induce a class of the hardest problems in terms of the epistasis variance and its variants. These analyses suggest that the existing quantitative measures cannot discriminate among symmetric functions, which reveals critical limitations of the measures. To take a closer look at the symmetric functions, additional analyses are performed from other viewpoints including additive separability and boundedness. It is shown that additive separability in a symmetric function is closely related to the symmetry of its subfunctions. This elucidates why most of the well-known symmetric fitness functions are additively inseparable. The properties of two-bounded symmetric functions are investigated and they are utilized in designing an efficient algorithm to check additive separability for the two-bounded functions. Throughout this paper, we heavily use the generalized Walsh transform over multary alphabets. Our results have an independent interest as a nontrivial application of the generalized Walsh analysis.

Optimal query complexity bounds for finding graphs

We consider the problem of finding an unknown graph by using queries with an additive property. This problem was partially motivated by DNA shotgun sequencing and linkage discovery problems of artificial intelligence. Given a graph, an additive query asks the number of edges in a set of vertices while a cross-additive query asks the number of edges crossing between two disjoint sets of vertices. The queries ask the sum of weights for weighted graphs. For a graph G with n vertices and at most m edges, we prove that there exists an algorithm to find the edges of G using O(mlogn^2mlog(m+1)) queries of both types for all m. The bound is best possible up to a constant factor. For a weighted graph with a mild condition on weights, it is shown that O(mlognlogm) queries are enough provided m>=(logn)^@a for a sufficiently large constant @a, which is best possible up to a constant factor if m=0. This settles, in particular, a conjecture of Grebinski [V. Grebinski, On the power of additive combinatorial search model, in: Proceedings of the 4th Annual International Conference on Computing and Combinatorics (COCOON 1998), Taipei, Taiwan, 1998, pp. 194-203] for finding an unweighted graph using additive queries. We also consider the problem of finding the Fourier coefficients of a certain class of pseudo-Boolean functions as well as a similar coin weighing problem.

Normalization for neural network in genetic search

Jung-Hwan Kim School of Computer Science and Engineering Seoul National University Shilim-dong, Kwanak-gu, Seoul, 151-742 Korea aram@soar.snu.ac.kr Sung-Soon Choi School of Computer Science and Engineering Seoul National University Shilim-dong, Kwanak-gu, Seoul, 151-742 Korea sschoi@soar.snu.ac.kr Byung-Ro Moon School of Computer Science and Engineering Seoul National University Shilim-dong, Kwanak-gu, Seoul, 151-742 Korea moon@soar.snu.ac.kr

Neural Network Normalization for Genetic Search

An arbitrary neural network has a number of functionally equivalent other networks. This causes redundancy in genetic representation of neural networks, which considerably undermines the merit of crossover in GAs [1]. This problem has received considerable attention in the past and has also been called the “competing conventions” problem [2].