Sentence examples for between two input vectors from inspiring English sources

In this case, the covariance between two input vectors can be defined as: Cov x i, x j = e − 1 2 ∑ p = 1 P x p i − x p j 2 l p 2 (6).

Thus, goal-specific neurons begin to disappear when around 92% of the possible distance between two input vectors can be explained from the motion component alone.

In other words, the critical question is how much of the maximal distance between two input vectors can be explained solely by the maximal distance between the two motion-encoding components.

It is clear from Figures 6 and 7 that the distance at which the kernel output reaches approximately zero varies with σ, and therefore the choice of σ for this kernel is essential in properly distinguishing the level of similarity between two input vectors.

Since the β values of interest are larger than 1, the maximally possible distance between two input vectors composed of vectors encoding the same motion primitive but different contextual information is larger than the same distance between input vectors composed of vectors encoding the same contextual information but different motion primitives.

Since the input vector in this case is a concatenation of two vectors, the relative importance of the individual components for the organization of the SOM is a function of how much of the maximal distance between two input vectors (Eq.  6) can be explained by these components individually.

The Gaussian and Exponential RBF kernels use the Euclidean distance between the two input vectors as a measure of similarity instead of the angle between them (see Figures 6 and 7).

The optimum mapping path between the two input vectors can also be found by backtracking the optimum path of each node.

And two input vectors, i.e. the minimal and maximal input vectors, are dimension-wisely assembled by the minimal and maximal points of all sectional curves.

This program accepts two input vectors, A and B, and calculates from them individual informational entropies H(A) and H(B), the entropy of the pair H A,B), and the mutual information between A and B, I(A B) = H(A)+H(B -H A,B -H A

The remaining four input vectors are selected using the most common approach in which selection of the input vector comprising of the sequential time series data.