Michael I. Jordan

TL;DR: A structure composed of local linear perceptrons for approximating global class discriminants is investigated and it is concluded that even on such a high-dimensional problem, such local models are promising, much better than RBF's and use much less memory.

TL;DR: A statistical mechanical framework for the modeling of discrete time series is proposed, and maximum likelihood estimation is done via Boltzmann learning in one-dimensional networks with tied weights, which motivates new architectures that address particular shortcomings of HMMs.

TL;DR: This paper provides a systematic methodology for converting continuous-time dynamics into discrete-time algorithms while retaining oracle rates, based on ideas from Hamiltonian dynamical systems and symplectic integration.

TL;DR: Two neural networks are developed with architecture similar to Zipser and Andersen's model and trained to perform the same task using a more biologically plausible learning procedure than backpropagation, which corroborates the validity of this neural network's computational algorithm as a plausible model of how area 7a may perform coordinate transformations.

TL;DR: In this article, a Bayesian nonparametric approach to speaker diarization is proposed, which builds on the hierarchical Dirichlet process hidden Markov model (HDP-HMM) of Teh et al.