ACC Coolen, journal publications since 2000

Neural information processing systems

ACC Coolen and D Saad, Phys. Rev. E62 (2000), 5444-5487
Dynamics of learning with restricted training sets

NS Skantzos and ACC Coolen, J.Phys. A33 (2000), 5785-5807
1+\infty Dimensional attractor neural networks

ACC Coolen, D Saad and YS Xiong, Europhys. Lett. 51 (2000), 691-697
On-line learning from restricted training sets in multilayer neural networks

HC Rae, JAF Heimel and ACC Coolen, J. Phys. A33 (2000), 8703-8722
Non-deterministic learning dynamics in large neural networks due to structural data bias

ACC Coolen and CWH Mace, in Neural Information Processing Systems XII (2000) (MIT press), SA Solla, TK Leen, KR Mueller (Eds), 237-243
Dynamics of supervised learning with restricted training sets and noisy teachers

NS Skantzos and ACC Coolen, J.Phys.A34 (2001), 929-942
Attractor modulation and proliferation in 1+\infty dimensional neural networks

JI Inoue and ACC Coolen, J.Phys.A34 (2001), L401-L408
Dynamics of on-line Hebbian learning with structurally unrealizable restricted training sets

JAF Heimel and ACC Coolen, J.Phys.A34 (2001), 9009-9026
Supervised learning with restricted training sets: a generating functional analysis

ACC Coolen, in Handbook of Biophysics Vol 4 (2001) (Amsterdam: Elsevier) 531-596
Statistical mechanics of recurrent neural networks I: statics

ACC Coolen, in Handbook of Biophysics Vol 4 (2001) (Amsterdam: Elsevier) 597-662
Statistical mechanics of recurrent neural networks II: dynamics

T Uezu and ACC Coolen, J.Phys.A35 (2002), 2761-2809
Hierarchical self-programming in recurrent neural networks

ACC Coolen and V Del Prete, Rev. Neurosci. 14 (2003), 181-193
Statistical mechanics beyond the Hopfield model: solvable problems in neural network theory

JPL Hatchet JPL and ACC Coolen, J.Phys.A37 (2004) 7199-7212
Asymmetrically Extremely Dilute Neural Networks with Langevin Dynamics and Unconventional Results

B Wemmenhove, NS Skantzos and ACC Coolen, J.Phys.A37 (2004) 7653-7670
Slowly Evolving Connectivity in Recurrent Neural Networks I: The Extreme Dilution Regime