Maximizing the robustness of a linear threshold classifier with discrete weights

References

• Amaldi E, Mayoraz E, de Werra D. A review of combinatorial problems arising in feedforward neural network design. Discrete Appl. Math. 1994; 52(1)
   Google Scholar
• Amaldi E, Nicolis S. Stability-capacity diagram of a neural network with Ising bonds. J. Physique 1989; 50: 2333–45
   Google Scholar
• Bouten M, Komoda A, Serneels R. Storage capacity of a diluted neural network with ising couplings. J. Phys. A: Math. Gen. 1990; 23: 2605–11
   Google Scholar
• Chvatal V. Linear Programming. Freeman, New York 1983
   Google Scholar
• Cook W, Gerards A M H, Schrijver A, Tardos E. Sensitivity theorems in integer linear programming. Mathematical Programming 1986; 34: 251–64
   Web of Science ®Google Scholar
• Costa D. An evolutionary tabu search algorithm and the NHL scheduling problem. Preprint. Swiss Federal Institute of Technology, Department of Mathematics. 1992, ORWP 92/11
   Google Scholar
• CPLEX Optimization Inc. CPLEX 1.2. 1990, 7710-T Cherry Park, Suite 124, Houston, TX 77095, USA
   Google Scholar
• Frean M. A thermal perceptron learning rule. Neural Computation 1992; 4: 946–57
   Web of Science ®Google Scholar
• Gallant S I. Perceptron-based learning algorithms. IEEE Trans. Neural Networks 1990; 1: 179–91
   PubMedGoogle Scholar
• Glover F. ‘Tabu search’ part I. ORSA J. Comput. 1989; 1: 190–206
   Google Scholar
• Glover F, Laguna M, Taillard E, de Werra D. Tabu Search, Annals of Operation Research, F Glover, et al. Baltzer, Basel 1993; 41, no 1-4
   Google Scholar
• Gutfreund H, Stein Y. Capacity of neural networks with discrete synaptic couplings. J. Phys. A: Math. Gen. 1990; 23: 2613–30
   Google Scholar
• Hassoun M H, Song J. Adaptive Ho-Kashyap rules for perceptron training. IEEE Trans. on Neural Networks 1992; 3: 51–61
   PubMed Web of Science ®Google Scholar
• Hertz A, de Werra D. Using tabu search techniques for graph coloring. Computing 1987; 29: 345–51
   Google Scholar
• Hertz A, de Werra D. The tabu search metaheuristic: How we used it. Annals Math. Artificial Intelligence 1991; 1: 111–21
   Google Scholar
• Horner H. Dynamics of learning for the binary perceptron problem. Z. Phys. 1992; B 86: 291–308
   Google Scholar
• Kirkpatrick S, Gelatt C D, Vecchi M P. Optimization by simulated annealing. Science 1983; 220: 671
   PubMed Web of Science ®Google Scholar
• Köhler H M. Adaptive genetic algorithm for the binary perceptron problem. J. Phys. A: Math. Gen. 1990; 23: L1265–71
   Google Scholar
• Krauth W, Mézard M. Learning algorithms with optimal stability in neural networks. J. Phys. A: Math. Gen. 1987; 20: L745–52
   Google Scholar
• Krauth W, Mézard M. Storage capacity of memory networks with binary couplings. J. Physique 1989; 50: 3057–66
   Google Scholar
• Krauth W, Opper M. Critical storage capacity of the j = ± 1 neural networks. J. Phys. A: Math. Gen. 1989; 22: L519–23
   Google Scholar
• Mayoraz E. Benchmark of some learning algorithms for single layer and Hopfield networks. Complex Systems 1990; 4: 477–490
   Google Scholar
• Mayoraz E. On the power of networks of majority functions. Proc. IWANN'91 (Lecture Notes in Computer Science 540), A Prieto. Springer, Berlin 1991; 78–85
   Google Scholar
• Mayoraz E. Maximizing the stability of a majority perceptron using tabu search. Proc. IJCNN'92 (Baltimore 1992) 1992; II254-9
   Google Scholar
• Mayoraz E. On the power of democratic networks. Swiss Federal Institute of Technology, Department of Mathematics. 1993, Technical Report, ORWP 93/2
   Google Scholar
• Mayoraz E, Aviolat F. Constructive training methods for feedforward neural networks with binary weights. Preprint ORWP. Swiss Federal Institute of Technology, Department of Mathematics. 1993
   Google Scholar
• Moscato P. An introduction to population approaches for optimization and hierarchical objective functions: A discussion on the role of tabu search. Tabu Search, Annals of Operation Research 1993; 41(1–4)85–121, ed F Glover et al (Basel: Baltzer)
   Google Scholar
• Papadimitriou C H, Steiglitz K. Combinatorial Optimization: Algorithms and Complexity. Prentice-Hall, Englewood Cliffs, NJ 1982
   Google Scholar
• Pérez C J, Vincent, Carrabina J, Valderrama E. Study of learning algorithm for neural network with discrete synaptic couplings. Network 1992; 3: 165–76
   Web of Science ®Google Scholar
• Robert V. Détermination d'une fonction majorité maximisant la stabilité. Travail de diplôme. École Polytechnique Fédérale de Lausanne, Département de Mathématiques. 1991
   Google Scholar
• Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 1958; 63: 386–408
   Google Scholar
• Taillard E. Recherche Itérative Dirigée Paralléle. PhD thesis. École Polytechnique Fédérale de Lausanne, Département de Mathématiques. 1993
   Google Scholar
• Venkatesh S. Directed drift: A new linear threshold algorithm for learning binary weights on-line. J. Comput. System Sci. 1989; 46: 198–217
   Google Scholar
• Verleysen M, Sirletti B, Vandermeulebroecke A, Jespers P. A high-storage capacity content-addressable memory and its learning algorithm. IEEE Trans. Circuits Systems 1989; 36: 762–6
   Google Scholar
• Widrow B, Hoff M E. Adaptive switching circuits. IRE WESCON Convention Record. IRE, New York 1960; 96–104
   Google Scholar