PubMed HealthSearch

Biomedical subjects

R M Neal

Publications and source records attributed to R M Neal.

6 recordsLinked to original sources

The "wake-sleep" algorithm for unsupervised neural networks.

An unsupervised learning algorithm for a multilayer network of stochastic neurons is described. Bottom-up "recognition" connections convert the input into representations in successive hidden layers, and top-down "generative" connections reconstruct the representation in one layer from the representation in the layer above. In the "wake" phase, neurons are driven by recognition connections, and generative connections are adapted to increase the probability that they would reconstruct the correct activity vector in the layer below. In the "sleep" phase, neurons are driven by generative connections, and recognition connections are adapted to increase the probability that they would produce the correct activity vector in the layer above.

Algorithms

The Helmholtz machine.

Discovering the structure inherent in a set of patterns is a fundamental aim of statistical inference or learning. One fruitful approach is to build a parameterized stochastic generative model, independent draws from which are likely to produce the patterns. For all but the simplest generative models, each pattern can be generated in exponentially many ways. It is thus intractable to adjust the parameters to maximize the probability of the observed patterns. We describe a way of finessing this combinatorial explosion by maximizing an easily computed lower bound on the probability of the observations. Our method can be viewed as a form of hierarchical self-supervised learning that may relate to the function of bottom-up and top-down cortical processing pathways.

Algorithms

Time as a factor in atmospheric sampling.

Differences in results of simultaneous air monitoring of ozone with three different methods in the field are described. The argument is advanced that the differences are due largely to sampling turbulent atmospheres with instruments utilizing different sampling intervals and time constants. It is concluded that when sampling natural turbulent atmospheres, a stable mean value can only be achieved through integrated sampling periods of greater than ten minutes.

Air

Liquid chromatographic determination of sulfamethazine in feeds.

A reverse-phase liquid chromatographic method for the assay of sulfamethazine (SMZ) in feeds is described. Feed samples are extracted with 50% methanol solution, centrifuged, filtered, and diluted when necessary, and chromatographed on a C-18 column. Samples are eluted with a mobile phase of 20% methanol and 80% of a solution containing acetic acid and tetramethylammonium chloride. The average recovery from spiked samples was 97.2% with a coefficient of variation of 1.2%. Linearity was very good (correlation coefficient 0.9997). Within-day and between-day coefficients of variation averaged 1.3 and 2.6%, respectively. The results for samples assayed by this method compared closely with the results from the same extracts assayed by the AOAC colorimetric method.

Animal Feed