Part of Advances in Neural Information Processing Systems 10 (NIPS 1997)
Nicholas Socci, Daniel Lee, H. Sebastian Seung
A simple but powerful modification of the standard Gaussian dis(cid:173) tribution is studied. The variables of the rectified Gaussian are constrained to be nonnegative, enabling the use of nonconvex en(cid:173) ergy functions. Two multimodal examples, the competitive and cooperative distributions, illustrate the representational power of the rectified Gaussian. Since the cooperative distribution can rep(cid:173) resent the translations of a pattern, it demonstrates the potential of the rectified Gaussian for modeling pattern manifolds.