| 503 | -- | 512 | Richard S. Zemel, Christopher K. I. Williams, Michael Mozer. Lending direction to neural networks |
| 513 | -- | 523 | Bernd-Jürgen Falkowski. Probabilistic perceptrons |
| 525 | -- | 535 | Gustavo Deco, Wilfried Brauer. Nonlinear higher-order statistical decorrelation by volume-conserving neural architectures |
| 537 | -- | 548 | Hilbert J. Kappen. Deterministic learning rules for boltzmann machines |
| 549 | -- | 562 | Juha Karhunen, Jyrki Joutsensalo. Generalizations of principal component analysis, optimization problems, and neural networks |
| 563 | -- | 569 | Ramana Vitthal, P. Sunthar, Ch. Durgaprasada Rao. The generalized proportional-integral-derivative (PID) gradient descent back propagation algorithm |
| 571 | -- | 577 | Paul L. Springer, Sandeep Gulati. Parallelizing the cascade-correlation algorithm using time warp |
| 579 | -- | 596 | Simone Santini, Alberto Del Bimbo. Properties of block feedback neural networks |
| 597 | -- | 603 | Roelof K. Brouwer. A method for training recurrent neural networks for classification by building basins of attraction |
| 605 | -- | 618 | Cheng-An Hung, Sheng-Fuu Lin. Adaptive hamming net: A fast-learning ART 1 model without searching |
| 619 | -- | 641 | Shaun Marriott, Robert F. Harrison. A modified fuzzy ARTMAP architecture for the approximation of noisy mappings |
| 643 | -- | 657 | Jayanta Basak, Nikhil R. Pal, Sankar K. Pal. A connectionist system for learning and recognition of structures: Application to handwritten characters |
| 659 | -- | 0 | Jagesh V. Shah, Chi-Sang Poon. Observations on characterization of training errors in supervised learning using gradient-based rules |
| 660 | -- | 0 | Jun Wang, Behnam Malakooti. Author s response |