### TABLE 1. Transitive m-systems of finite polar spaces admitting an insoluble group with non-abelian composition factor S.

### Table 2: Coe cients for network apos;s evolution: rates of change for Ds,Dt,Dn, and average segment length of each type, ratio of NCC apos;s to intercommutation events, and cumulative number of NCC apos;s per node, reported for di erent conditions. The nal row gives Z3 results. Abbreviations: LG=lattice gauge initial conditions, H=Higgs initial conditions, B=bridge NCC, Z=zipper NCC, R=rearrangements allowed, N=no rearrangements, IC=intercommutation, NCC=non-commutative collision. 47

"... In PAGE 40: ... A few representative plots are shown here in order to show their typical shapes. The remainder are summarized in Table2 , which gives their slopes. The last set of gures in this section, gures 25 - 27, consists of a series of histograms which show how the distribution of string segment lengths evolves with time.... In PAGE 40: ... Distributions are shown for two contrasting cases discussed below, and corresponding data is also provided for the Z3 network for the sake of comparison. The parameter space surveyed in Table2 includes two di erent initial condition simulations, several di erent ratios of the string tensions, and two other binary choices a ecting string collisions and close encounters between nodes. The choice between \bridge quot; and \zipper quot; con gurations for colliding non-Abelian strings is one choice (abbreviated B and Z in Table 2.... In PAGE 40: ... The parameter space surveyed in Table 2 includes two di erent initial condition simulations, several di erent ratios of the string tensions, and two other binary choices a ecting string collisions and close encounters between nodes. The choice between \bridge quot; and \zipper quot; con gurations for colliding non-Abelian strings is one choice (abbreviated B and Z in Table2 .) The other choice determines what happens when two neighboring nodes are within distance dann but are topologically unable to anni- hilate.... In PAGE 42: ... Apparently, after some transient behavior at very early times, a sort of dynamical equilibrium is established, with energy being transferred in a steady cascade from the t network to s network and then lost to damping. Interestingly, decreasing the even string tension still further to 0:25 does not allow the odd strings to contract more quickly (see Table2 ) { evidently they are impeded by the larger population of even strings. S3 network with heavy even strings A situation which contrasts with the case of light s strings is one in which the s strings have a large tension.... In PAGE 46: ... Rearrangements (quasi-intercommutations) of the connections of neighboring nodes evidently increase the mobility of ux, and increase the likelihood that eventually some neighboring pairs of nodes will be able to annihilate. As is apparent from Table2 , the inclusion of rearrangements almost invariably speeds up the decay of the network, often by roughly a factor of two. The choice of either zipper or bridge con gurations for colliding non-commuting strings generally makes a smaller di erence, if any.... ..."

### Table 4. Area and percent of used nodes SB- DDs and FNADDs for adders

"... In PAGE 3: ... We also show the number of non-terminal (ncn), the constant nodes (cn), and the percent of used nodes in the DD from the total of nodes in the corresponding decision trees. Table4 and Table 6 compare the area (CP BP D7DB) and percent of used nodes with respect to the toal of nodes in the decision trees of Shared BDDs (SBDDs) and Fourier DDs (FNADDs) on quaternion groups for adders for mul- tipliers. The discussed feature of non-Abelian groups be- comes especially important when we want to reduce the... ..."

### Table 1: Topological invariants in the perturbative and the non-perturbative regimes for d =3andd=4.

1211

"... In PAGE 4: ... It is not known at the moment which one is the situation for other groups and representations but one would expect that in general the invariants associated to non-abelian monopoles could be expressed in terms of some other simpler invariants, being Seiberg-Witten invariants just the rst subset of the full set of invariants. In Table1 we have depicted the present situation in three and four dimensions rela- tive to Chern-Simons gauge theory and Donaldson-Witten theory, respectively. These theories share some common features.... ..."

### Table 5: Hamming Distance from the Optimum for = 1 through 6.

1997

"... In PAGE 13: ... The increased degrees of freedom a orded functions with higher degrees of nonlinearity creates a more diverse set of functions yielding a wider possible range of attainable sum apos;s. Table5 shows for each set of functions, = 1 through 6, the number of times the in nite population model genetic algorithm converged to a point at a given Hamming distance after 20 generations. For instance, of the 100 fourth order functions tested, 11 converged to a point 2 bits away from the optimum point.... ..."

Cited by 1

### Table 3: Matrix H of Hamming distances between the rows of X.

"... In PAGE 7: ... Tables 3 and 4 present similarity matrices obtained from Table 1 con- sidered as a column-conditional table. Table3 is a distance matrix. Its #28i; j#29-th entry h ij is the number of noncoinciding components in the row- vectors, which is called Hamming distance.... ..."

### Table 3: Matrix H of Hamming distances between the rows of X.

"... In PAGE 7: ... Tables 3 and 4 present similarity matrices obtained from Table 1 con- sidered as a column-conditional table. Table3 is a distance matrix. Its #28i; j#29-th entry h ij is the number of noncoinciding components in the row- vectors, which is called Hamming distance.... ..."

### Table 2: Correlation between Hamming and SSIM scores

2004

"... In PAGE 4: ...01. The correlation coefficient between Hamming distance and SSIM is given in Table2 . In most of the attacks we observe very weak correlation because, as the SSIM de- creases gradually, the Hamming distance still tend to stay close to zero, which is required from a perceptual hash.... ..."

Cited by 3

### Table 1: The pairwise Hamming distances between the 10 test antigens used in the ex- perimental verification of the algorithm. The table is symmetric about the main diagonal because Hamming distance is commutative. The table shows that the antigens were at vari- ous Hamming distances from each other.

1998

"... In PAGE 5: ... These data were used to determine how much of each ball of stimulation was populated with clones generated by previous antigens. Table1 shows that the 10 antigens were at varying Hamming distances from each other and thus had varying overlaps. Table 2 shows that these overlaps resulted in many different proportions of balls of stimulation being populated by clones generated by prior antigens, and were thus a reason- able test of the lazy algorithm.... ..."

Cited by 6

### Table 3. Active learning vs. Passive learning.

2004

"... In PAGE 12: ... This is because Sc uses data catalog statistics to dif- ferentiate among the selection features, and picks those which can be excluded from the target query with high probability. Table3 compares the performance of both active learning strategies for Sphinx with two experiments in which Sphinx is hobbled to become a passive learning sys- tem. These two experiments do not represent valid strategies but are designed to iden- tify bounds, both lower (oracle) and upper (random) on the number of examples an active learning algorithm may require.... ..."

Cited by 2