Analytic Study of Complex Fractional Tsallis’ Entropy with Applications in CNNs

In this paper, we study Tsallis’ fractional entropy (TFE) in a complex domain by applying the definition of the complex probability functions. We study the upper and lower bounds of TFE based on some special functions. Moreover, applications in complex neural networks (CNNs) are illustrated to recognize the accuracy of CNNs.

The scheme of the axioms of probability theory placed in 1933 by Kolmogorov can be extended to include the imaginary set of numbers and this by accumulation to his original five axioms. Later, an additional three axioms were given in [16]. Consequently, the complex probability domain is defined by the sum of the real set S R with its corresponding real probability and the imaginary S M with its corresponding imaginary probability. In general, the advantages of complex probability theory are that it is considered a supplementary dimension (imaginary part) to the event appearing in the real dimension laboratory (real part). It represents physical quantities of complex networks in terms of currents, complex potentials and impedance. Moreover, it fulfills luck and chance in S R substituted by total determinism in a complex domain. Finally, it extends many well-known concepts of the traditional probability theory, such as expectation and variance, to the complex probability theory with more accuracy in applications. One of the important applications of complex probability theory is in realistic quantum mechanics [17]; for example, the two slit experiment where a source releases a single particle, which moves to a wall with two slits and is spotted at position χ on a shelter placed behind the wall. The typical argument that an interference design on the shelter infers that the particle did not either drive through one slit or the other is ultimately an argument in probability theory such that P(χ) = P(χ) 1 + P(χ) 2 , where P(χ) 1 and P(χ) 2 are the probability via the first and second slit, respectively, which is a critical process. This process leads to the use of complex probability theory.
Recently, Abou Jaoude [18] extended Shannon's information theory by using the complex probability. The author calculated the magnitude of the chaotic factor, the channel capacities in the probability and the degree of knowledge. In general, complex probability leads to better information for all processes compared to the classical probability [19,20]. Figure 1 shows the relation between complex analysis and information theory. Our investigation is based on the concept of complex probability to extend the idea of Tsallis' fractional entropy (TFE). The study of the technique delivered by using the approximation theory of special functions of complex variables was useful in information theory. We introduce the upper and lower bound of TFE. Sharpness is discussed as well in the sequel.

Results
Let A be an event in a complex domain S C . The real and imaginary terms of the complex probability function (CPF): P c (z) = P r (x, y) + P m (x, y) where the argument z = x + iy, and P r and P m are the real probability and the imaginary probability in the real set S R and imaginary set S M , respectively. Following Axiom 7 in [16], we have: such that z = x + iy with |z| 2 = P 2 r + (P m /i) 2 and P m = i(1 − P r ); hence, P c is always equal to one. Abou Jaoude et al. [19] inferred that z ∈ U = {z ∈ C : |z| < 1} (the open unit disk).
Tsallis presented an entropic formalization characterized by an index γ, which implies a non-extensive statistics. TFE (T γ ) is the basis of the so-known non-extensive statistical mechanics, which modifies the Boltzmann-Gibbs theory. Tsallis statistics has been used in various fields such as applied mathematics, physics, biology, chemistry, computer science, information theory, engineering, medicine, economics, business, geophysics, etc. Since we study the analytic properties of TFE, therefore, we focus on the continuous formula. The general continuous form of this entropy is given by: By applying the concept of CPF in Equation (1), we extend TFE into complex values as follows (CTFE ): For a special domain S C = U, we have: For the analytic study, we shall use the definition: where P c is analytic in U, having the form: It is clear that T γ (0) = 1 and (T γ ) > 0. TFE has been maximized by using different techniques depending on its parameter γ. This problem was discussed in [1,2] for real power index γ and in [21] for the complex power index. The authors showed that the Tsallis distribution reserves its fractional power formula, decorating with some specific log-periodic oscillations (convergence dynamics of z-logistic maps). As a result, the authors introduced a complex measure of the thermal bath heat capacity C = 1/(γ − 1). Thus, in general, the heat capacity becomes complex as well. In this work, CTFE approximates some special functions in a complex domain. These functions are popular in various applications.
Next, we approximate Equation (4) for some special functions. The advantageous of the approximation are: First, for recognizing target functions, the approximation technique studies how certain known functions (for example, special functions) can be approximated by a definite class of functions (for example, polynomials or rational functions) that often have desirable properties (inexpensive computation, continuity, integral and limit values, etc.). Second, the target function, call it Ψ, may be unknown; instead of a clear formula, only a set of points of the form (x, Ψ(x)) is delivered. Depending on the organization of the domain and codomain of Ψ, several methods for approximating g may be applicable. For example, if Ψ is an operation on the complex numbers, the techniques of geometric function theory can be used.
We have the following properties (upper bounds):
Proof. Let t, τ ∈ ∂U; then, we have: In view of Theorem 1.11 in [23], the 1+tz 1+τz γ admits a probability measure µ in (∂U) 2 satisfying: Then, by virtue of Proposition 1, there is a constant λ (diffusion constant) such that: This completes the proof.

Gaussian Function Φ(a, c; z)
The function Φ(a, c; z) is defined by the series: A special case of this function is Φ(a, a; z) = e z . We consider CTFE approximated by e −γz . Clearly, we have the following results: Proposition 3. For CTFE approximated by e −γz : By Proposition 3, we have the desired assertion.

Fractional Sigmoid Function FSF
CTFE can be approximated by FSF. In our investigation, we focus on the type of function, which is analytic in U. We suggest the function (see Figure 4): The expansion CTFE are given as follows: . . .
For sufficient values of a and c, CTFE approximated by FSF can be majorized by Φ(a, c; z).

Complex-Valued Neural Networks
CNNs are a necessary extension of the analysis of real-valued neural networks. CNNs are networks that utilize complex-valued variables and parameters, effectively distributing in this style with complex-valued information. They are very well matched with wave phenomena, and they are suitable for the procedures connected with complex altitude [25]. The have been used for a long list of applications, essentially in learning tasks, loss function, cost function, utility function and combinatorial optimization.
In CNNs, the neurons in each layer are systematized as a three-dimensional array rather than as a vector in ANNs (artificial neural networks). The first two dimensions are titled spatial, and the third is a partition to networks. The CNN system charts three ideologies characteristic of natural systems: locality, sharing and pooling.
The locality behavior is the information that neurons depend only on their neighbors, rather than on far away neurons. Sharing is the limitation that various pi neurons should undergo the same processing. It is challenging that an affine layer follows locality, and sharing results in a convolution layer. Pooling is used to indicate invariance to small translations. A pooling layer does so by splitting each input channel into patches and replacing each patch with a single representative assessment in the output layer.
Suppose the CNN is delivered by n fully connected in a Hopfield-like net. The output is given by a complex number for each neuron: Thus, the network state (information of the net) I γ (z k ), k = 1, ..., n is a complex vector. In this work, we shall use the total information, which is given by the relation: where T γ is approximated by Equation (9). Therefore, a large amount of information can be realized from both theoretical study and numerical computations from T γ (z). The stability of Equation (10) is given by the energy equation: whereĪ γ (z) is the conjugate of I γ (z). The energy provides a tool for studying the dynamics of CNNs. Figure 5 shows the steps of finding the energy. The minimum energy is bounded by the value ρ, which is suggested during the training of CNN. It has been shown by experiences, for a CNN of four neurons, that the minimum energy is satisfying Equation (11) for the output on ∂U as follows: The energy E γ is equal to one for all values γ > 2; while the energy is increasing for outcomes inside the unit disk U. For example, the output set: has energy E γ > 1, for different values of γ. Acknowledgments: The authors would like to express their thanks to the reviewers for their important and useful comments to improve the paper. The work here is partially supported by the Universiti Kebangsaan Malaysia grant: GUP ( Geran Universiti Penyelidikan)-2017-064.

Conflicts of Interest:
The authors declare no conflict of interest.

Abbreviations
The following abbreviations are used in this manuscript: γ parameter λ diffusion constant z complex number P c complex probability S R real set of events S M imaginary set of events P r probability in the real set P m probability in the imaginary set U the open unit disk |z| 2 the degree of our knowledge of the random experiment; it is the square of the norm of z T γ [P c ] CFTE (T γ ) the real part of CFTE Φ(a, c; z) Gaussian function Γ(.) gamma function I γ total information E γ the energy ρ the upper bound of energy