Abstract
The Continuous Hopfield Neural Network (CHN) is a neural network which can be used to solve some optimization problems. The weights of the network are selected based upon a set of parameters which are deduced by mapping the optimization problem to its associated CHN. When the optimization problem is the Traveling Salesman Problem, for instance, this mapping process leaves one free parameter; as this parameter decreases, better solutions are obtained. For the general case, a Generalized Quadratic Knapsack Problem (GQKP), there are some free parameters which can be related to the saddle point of the CHN. Whereas in simple instances of the GQKP, this result guarantees that the global optimum is always obtained, in more complex instances, this is far more complicated. However, it is shown how in the surroundings of the saddle point the attractor basins for the best solutions grow as the free parameter decreases, making saddle point neighbors excellent starting point candidates for the CHN. Some technical results and some computational experiences validate this behavior.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Demuth, H.B., Beale, M.H., De Jess, O., Hagan, M.T.: Neural Network Design. PWS Publishing Company, Boston (1996)
García, L., Talaván, P.M., Yáñez, J.: Improving the Hopfield model performance when applied to the traveling salesman problem. Soft Comput. 1–15 (2016). doi:10.1007/s00500-016-2039-8
Gopal, M.: Modern Control System Theory. New Age International, New Delhi (1993)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. Sci. 79(8), 2554–2558 (1982)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Nat. Acad. Sci. 81(10), 3088–3092 (1984)
Hopfield, J.J., Tank, D.W.: “Neural” computation of decisions in optimization problems. Biol. Cybern. 52(3), 141–152 (1985)
Koopmans, T.C., Beckmann, M.: Assignment problems and the location of economic activities. Econom.: J. Econom. Soc. 25, 53–76 (1957)
Reinelt, G.: TSPLIB. A traveling salesman problem library. ORSA J. Comput. 3(4), 376–384 (1991)
Rojas, R.: Neural Networks: A Systematic Introduction. Springer Science & Business Media, Heidelberg (2013)
Talaván, P.M., Yáñez, J.: Parameter setting of the Hopfield network applied to TSP. Neural Netw. 15(3), 363–373 (2002)
Talaván, P.M.: Ph.D. dissertation: El modelo de Hopfield aplicado a problemas de optimización combinatoria, Universidad Complutense de Madrid (2003)
Talaván, P.M., Yáñez, J.: The generalized quadratic knapsack problem. A neuronal network approach. Neural Netw. 19(4), 416–428 (2006)
Acknowledgments
This research has been partially supported by the Government of Spain, grant TIN2015-66471-P, and by the local Government of Madrid, grant S2013/ICE-2845 (CASI-CAM).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Some Technical Results of the Illustrative Example
A Some Technical Results of the Illustrative Example
Recalling the GQKP problem introduced in Sect. 2, a stability analysis of the valid solutions is carried out, looking for the parameters that guarantee that the CHN is stable in the feasible solutions. The energy function obtained for the simple GQKP problem (see Eq. 3) was:
Referencing Talaván and Yáñez [12], the stability of any \(\mathbf {v} \in H\) is ensured if:
where
Although analyzing all feasible solutions would be a very difficult task with a GQKP, this simple example allows rigorous analysis. Thus, the partial derivatives of the energy function will be of the form:
Condition 4 is satisfied if:
and Condition 5 is satisfied if:
This example does not use Condition 6 as no slack variables are needed.
The instability of any interior point \(\mathbf {v} \in H \setminus H_C\) is guaranteed if:
and the stability of valid solutions is obtained if \(\mathbf {\varPhi }\) is positive semidefinite:
The instability of any non-feasible corner is obtained by creating a partition of the set \(H_{C}\setminus H_{F}\) and forcing the instability conditions for each of the elements in the partition:
Going forward the partition \(H_C \setminus H_F\) is created using the direct method introduced by Talaván [11]. In summary, this partition is created considering the different cases which may occur when the constraints for \(H_F\) are violated. Thus, given \(\mathbf {v} \in H_C \setminus H_F\), the instability will be found from the first unsatisfied constraint, distinguishing inequalities and equations (which may not be satisfied by excess or defect):
where
For the GQKP problem being studied, the partition gets reduced to:
where
-
\(W_{1,1} = \{e_{1}(\mathbf {v})\> 1\} = \{ v_{1} + v_{2} > 1\} \), which is satisfied if \(v_{1} = 1\) and \(v_{2} = 1\):
$$ \left\{ \begin{array}{l} E_{1}(\mathbf {v})> {-}4\alpha + 2\phi _{1,1} - \gamma _{1} + \beta _{1}\\ E_{2}(\mathbf {v}) > -2\alpha + 2\phi _{1,1} - \gamma _{2} + \beta _{1} \end{array} \right. $$and the instability is guaranteed if:
$$ \vee \left\{ \begin{array}{l} {-}4\alpha + 2\phi _{1,1} - \gamma _{1} + \beta _{1} \ge \varepsilon \\ -2\alpha + 2\phi _{1,1} - \gamma _{2} + \beta _{1} \ge \varepsilon \end{array} \right. $$ -
\(W_{1,2} = \{e_{1}(\mathbf {v})< 1\} = \{ v_{1} + v_{2} < 1\}\), which is satisfied if \(v_{1} = 0\) y \(v_{2} = 0\):
$$ \left\{ \begin{array}{l} E_{1}(\mathbf {v}) \le \gamma _{1} + \beta _{1}\\ E_{2}(\mathbf {v}) \le \gamma _{2} + \beta _{1} \end{array} \right. $$and the instability is guaranteed if:
$$ \vee \left\{ \begin{array}{l} \gamma _{1} + \beta _{1} \le -\varepsilon \\ \gamma _{2} + \beta _{1} \le -\varepsilon \end{array} \right. $$
Therefore, considering the initial conditions and choosing from the recently obtained inequalities, the following set of linear inequalities guarantees the stability of feasible solutions and instability of non-feasible ones:
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
García, L., Talaván, P.M., Yáñez, J. (2017). Attractor Basin Analysis of the Hopfield Model: The Generalized Quadratic Knapsack Problem. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2017. Lecture Notes in Computer Science(), vol 10305. Springer, Cham. https://doi.org/10.1007/978-3-319-59153-7_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-59153-7_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59152-0
Online ISBN: 978-3-319-59153-7
eBook Packages: Computer ScienceComputer Science (R0)