Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Introduction to the theory of neural computation
This book is a detailed, logically-developed treatment that covers the theory and uses of collective computational networks, including associative memory, feed forward networks, and unsupervised learning. Expand
Introduction to the Theory of Neural Computation
A Simple Weight Decay Can Improve Generalization
It is proven that a weight decay has two effects in a linear network, and it is shown how to extend these results to networks with hidden layers and non-linear units. Expand
Adjacent visual cortical complex cells share about 20% of their stimulus-related information.
It is hypothesized that this trend toward independence of information processing by adjacent cortical neurons is a general organizational strategy used to maximize the amount of information carried in local groups. Expand
Coarse-grained reverse engineering of genetic regulatory networks.
A method for determining the parameters of genetic regulatory networks, given expression level time series data, is introduced and evaluated using artificial data and applied to a set of actual expression data from the development of rat central nervous system. Expand
Modeling Genetic Regulatory Dynamics in Neural Development
It is found that generally a single time series is of limited value in determining the interactions in the network, but multiple time series collected in related tissues or under treatment with different drugs can fix their values much more precisely. Expand
Cumulants of Hawkes point processes.
- S. Jovanovic, J. Hertz, S. Rotter
- Mathematics, Medicine
- Physical review. E, Statistical, nonlinear, and…
- 18 September 2014
We derive explicit, closed-form expressions for the cumulant densities of a multivariate, self-exciting Hawkes point process, generalizing a result of Hawkes in his earlier work on the covariance… Expand
Generalization in a linear perceptron in the presence of noise
The authors study the evolution of the generalization ability of a simple linear perceptron with N inputs which learns to imitate a 'teacher perceptron'. The system is trained on p= alpha N example… Expand