Biomedical subjects

Seiji Miyoshi

Publications and source records attributed to Seiji Miyoshi.

4 recordsLinked to original sources

PubMed2005

Analysis of ensemble learning using simple perceptrons based on online learning theory.

Ensemble learning of K nonlinear perceptrons, which determine their outputs by sign functions, is discussed within the framework of online learning and statistical mechanics. One purpose of statistical learning theory is to theoretically obtain the generalization error. This paper shows that ensemble generalization error can be calculated by using two order parameters, that is, the similarity between a teacher and a student, and the similarity among students. The differential equations that describe the dynamical behaviors of these order parameters are derived in the case of general learning rules. The concrete forms of these differential equations are derived analytically in the cases of three well-known rules: Hebbian learning, perceptron learning, and AdaTron (adaptive perceptron) learning. Ensemble generalization errors of these three rules are calculated by using the results determined by solving their differential equations. As a result, these three rules show different characteristics in their affinity for ensemble learning, that is "maintaining variety among students." Results show that AdaTron learning is superior to the other two rules with respect to that affinity.

Journal Article↗

PubMed2005

Novel immunosuppressive therapy by M2000 in experimental multiple sclerosis.

The therapeutic potency of M2000 (beta-D-mannuronic acid), a novel designed nonsteroidal anti-inflammatory drug with immunosuppressive property in T-cell-mediated autoimmune disease, was tested. The influence of M2000 on myelin basic protein (MBP)-induced experimental autoimmune encephalomyelitis (EAE), an animal model of multiple sclerosis, was assessed. M2000 at two doses, 40 and 80 mg/kg/day, was administered intraperitoneally (i.p.) to prevention and treatment groups, respectively. Onset of i.p. injections of M2000 to prophylactic and therapeutic groups was day-1 and day-7 postimmunization. The WEHI-164 cell line was used for assaying the tolerability against M2000. The results of this experiment showed that the treatment of EAE with M2000 could significantly suppress disease development both prophylactically and therapeutically; the onset and symptoms of EAE in Lewis rats could be suppressed following the administration of M2000. Clinical improvement was accompanied by a marked decrease in mean numbers of vessels with perivascular cellular infiltration in M2000-treated rats compared with nontreated control. Disease suppression was associated with a marked suppression of MBP-specific T-cell reactivity in vitro, without any evidence for a generalized impairment of T-cell activity. Moreover, M2000 also showed a very high tolerability compared with certain steroidal and nonsteroidal anti-inflammatory drugs. Collectively, our data suggest that M2000 may provide a novel therapeutic option for T-cell-mediated autoimmune diseases in animal models and possibly in humans.

Animals↗

PubMed2004

Associative memory by recurrent neural networks with delay elements.

The synapses of real neural systems seem to have delays. Therefore, it is worthwhile to analyze associative memory models with delayed synapses. Thus, a sequential associative memory model with delayed synapses is discussed, where a discrete synchronous updating rule and a correlation learning rule are employed. Its dynamic properties are analyzed by the statistical neurodynamics. In this paper, we first re-derive the Yanai-Kim theory, which involves macrodynamical equations for the dynamics of the network with serial delay elements. Since their theory needs a computational complexity of O(L4t) to obtain the macroscopic state at time step t where L is the length of delay, it is intractable to discuss the macroscopic properties for a large L limit. Thus, we derive steady state equations using the discrete Fourier transformation, where the computational complexity does not formally depend on L. We show that the storage capacity alphaC is in proportion to the delay length L with a large L limit, and the proportion constant is 0.195, i.e. alphaC=0.195L. These results are supported by computer simulations.

Association Learning↗

PubMed2004

Storage capacity diverges with synaptic efficiency in an associative memory model with synaptic delay and pruning.

It is known that storage capacity per synapse increases by synaptic pruning in the case of a correlation-type associative memory model. However, the storage capacity of the entire network then decreases. To overcome this difficulty, we propose decreasing the connectivity while keeping the total number of synapses constant by introducing delayed synapses. In this paper, a discrete synchronous-type model with both delayed synapses and their prunings is discussed as a concrete example of the proposal. First, we explain the Yanai-Kim theory by employing statistical neurodynamics. This theory involves macrodynamical equations for the dynamics of a network with serial delay elements. Next, considering the translational symmetry of the explained equations, we rederive macroscopic steady-state equations of the model by using the discrete Fourier transformation. The storage capacities are analyzed quantitatively. Furthermore, two types of synaptic prunings are treated analytically: random pruning and systematic pruning. As a result, it becomes clear that in both prunings, the storage capacity increases as the length of delay increases and the connectivity of the synapses decreases when the total number of synapses is constant. Moreover, an interesting fact becomes clear: the storage capacity asymptotically approaches 2/pi due to random pruning. In contrast, the storage capacity diverges in proportion to the logarithm of the length of delay by systematic pruning and the proportion constant is 4/pi. These results theoretically support the significance of pruning following an overgrowth of synapses in the brain and may suggest that the brain prefers to store dynamic attractors such as sequences and limit cycles rather than equilibrium states.

Action Potentials↗