Biomedical subjects

D S Yeung

Publications and source records attributed to D S Yeung.

6 recordsLinked to original sources

PubMed2005

Sensitivity analysis applied to the construction of radial basis function networks.

Conventionally, a radial basis function (RBF) network is constructed by obtaining cluster centers of basis function by maximum likelihood learning. This paper proposes a novel learning algorithm for the construction of radial basis function using sensitivity analysis. In training, the number of hidden neurons and the centers of their radial basis functions are determined by the maximization of the output's sensitivity to the training data. In classification, the minimal number of such hidden neurons with the maximal sensitivity will be the most generalizable to unknown data. Our experimental results show that our proposed sensitivity-based RBF classifier outperforms the conventional RBFs and is as accurate as support vector machine (SVM). Hence, sensitivity analysis is expected to be a new alternative way to the construction of RBF networks.

Algorithms↗

PubMed1999

Neocognitron's parameter tuning by genetic algorithms.

The further study on the sensitivity analysis of Neocognitron is discussed in this paper. Fukushima's Neocognitron is capable of recognizing distorted patterns as well as tolerating positional shift. Supervised learning of the Neocognitron is fulfilled by training patterns layer by layer. However, many parameters, such as selectivity and receptive fields are set manually. Furthermore, in Fukushima's original Neocognitron, all the training patterns are designed empirically. In this paper, we use Genetic Algorithms (GAs) to tune the parameters of Neocognitron and search its reasonable training pattern sets. Four contributions are claimed: first, by analyzing the learning mechanism of Fukushima's original Neocognitron, the correlations amongst the training patterns are claimed to affect the performance of Neocognitron, tuning the Neocognitron's number of planes is equivalent to searching reasonable training patterns for its supervised learning; second, a GA-based supervised learning of the Neocognitron is carried out in this way, searching the parameters and training patterns by GAs but specifying the connection weights by training the Neocognitron; third, other than traditional GAs which are unsuitable for the large searching space of training patterns set, the cooperative coevolution is incorporated to play this role; fourth, an effective fitness function is given out when applying the above methodology into numeral recognition. The evolutionary computation in our initial experiments is implemented based on the original training pattern set, e.g. the individuals of the population are generated from Fukushima's original training patterns during initialization of GAs. The results prove that our correlation analysis is reasonable, and show that the performance of a Neocognitron is sensitive to its training patterns, selectivity and receptive fields, especially, the performance is not monotonically increasing with respect to the number of training patterns, and this GA-based supervised learning is able to improve Neocognitron's performance.

Cognition↗

PubMed1997

Human telomerase contains evolutionarily conserved catalytic and structural subunits.

We have cloned and characterized a human gene encoding TP2 (telomerase-associated protein 2), a protein with similarity to reverse transcriptases and the catalytic telomerase subunits from Saccharomyces cerevisiae and Euplotes aediculatus. Indirect immunofluorescence revealed that TP2 was localized to the nucleus. Using antibodies to endogenous and epitope-tagged TP2, we found that TP2 was associated specifically with human telomerase activity and the recently identified telomerase-associated protein TP1. Mutation of conserved residues within the reverse transcriptase domain of TP2 severely reduced associated telomerase activity. These results suggest that telomerase is an evolutionarily conserved multisubunit complex composed of both structural and catalytic subunits.

Amino Acid Sequence↗

PubMed1994

Incorporating production rules with spatial information onto a neocognitron neural network.

Rule-embedded neocognitron (REN) is proposed where the knowledge base of a neocognitron is constructed through incorporating production rules into its interlayer connections. Prototype patterns training is not required. The semantic of interlayer connections is established. The resulting network can now be analyzed according to the rule structure and problematic portions can be corrected. We demonstrate the ease with which performance can be improved by applying REN on handwritten numeral recognition. The same set of handwritten numerals initiated by Fukushima is used to test this methodology. It is found that the performance is comparable with that of Fukushima's neocognitron with supervised training.

Algorithms↗

PubMed1994

A hybrid cognitive system using production rules to synthesize neocognitrons.

A hybrid cognitive system is proposed where a working neocognitron is synthesized with a set of production rules. The knowledge base of a neocognitron is constructed through incorporating production rules into its interlayer connections. Training for prototype patterns is not required. The semantic of interlayer connections is established. The resulting network can now be analyzed according to the rule structure and problematic portions can be corrected. Neocognitrons constructed using this hybrid approach have been tested on the same set of handwritten numerals initiated by Fukushima with scaling and skewing distortions, and with noise contamination. It is found that the performance is comparable to that of Fukushima's network obtained by supervised training.

Cognition↗

PubMed1992

Cytoskeletal changes in hepatocytes induced by Microcystis toxins and their relation to hyperphosphorylation of cell proteins.

The heptapeptide toxins produced by the blue-green alga (cyanobacterium) Microcystis aeruginosa are selectively hepatotoxic in mammals. The characteristic post-mortem pathology of the liver is extensive lobular disruption due to sinusoidal breakdown, leakage of blood into the tissue and hepatocyte disintegration. Isolated hepatocytes incubated with toxin show severe structural deformity and surface blebbing. This paper demonstrates the effects of Microcystis toxins on the contraction and aggregation of actin microfilaments, and on the relocation and breakdown of cytokeratin intermediate filaments, in cultured hepatocytes. Earlier work did not show changes in the assembly/disassembly of actin; however, this paper demonstrates the change in cytokeratin from intermediate filaments to distributed granules in the cytoplasm of toxin-affected cells. Acrylamide gel electrophoresis of cytoskeletal fractions from hepatocytes did not show changes in total cytokeratins; however, marked changes in the immunogenicity of cytokeratins at 52 and 58 kDa were seen on toxin exposure of cells. Measurement of 32P-phosphorylation of proteins in toxin-affected cells incubated with [32P]orthophosphate showed a dramatic increase compared to control incubations. This is in agreement with research elsewhere describing phosphatase inhibition in vitro by Microcystis toxins. The data indicate that phosphorylated cytokeratin is a major component of cytoplasmic fraction phosphorylated protein after toxin exposure to hepatocytes. It is concluded that the mechanism of Microcystis toxicity to the hepatocyte is through cytoskeletal damage leading to loss of cell morphology, cell to cell adhesion and finally cellular necrosis. The underlying biochemical lesion is likely to be phosphatase inhibition causing hyperphosphorylation of a number of hepatocyte proteins, including those cytokeratins responsible for microfilament orientation and intermediate filament integrity.

Actins↗