We study the role of sizes of neural networks (NNs) in TRAP (TempoRAl Patterns) and HATS (Hidden Activation TRAPS architecture) probabilistic features extraction. The question of sufficient size of band NNs is linked with the question whether the Merger is able to compensate for lower accuracy of band NNs. For both architectures, the performance increases with increasing size of Merger NN. For ...

The nonnutritive suck (NNS) is an observable and accessible motor behavior which is often used to make inference about brain development and pre-feeding skill in preterm and term infants. The purpose of this study was to model NNS burst compression pressure dynamics in the frequency and time domain among two groups of preterm infants, including those with respiratory distress syndrome (RDS, N =...

AIMS To evaluate the impact on perinatal outcomes of universal gestational diabetes (GDM) screening based on 1999 WHO and IADPSG diagnostic criteria; to assess the quality of the evidence (GRADE) to support GDM screening. METHODS Simulation of a hypothetical cohort of community-based pregnant women with 10% GDM prevalence (1999 WHO). Most parameters were obtained from recent systematic review...

BACKGROUND Non-nutritive sweeteners (NNS), especially in form of diet soda, have been linked to metabolic derangements (e.g. obesity and diabetes) in epidemiologic studies. We aimed to test acute metabolic effects of NNS in isolation (water or seltzer) and in diet sodas. METHODS We conducted a four-period, cross-over study at the National Institutes of Health Clinical Center (Bethesda, Maryla...

In this article we present EANT2, a method that creates neural networks (NNs) by evolutionary reinforcement learning. The structure of NNs is developed using mutation operators, starting from a minimal structure. Their parameters are optimised using CMA-ES. EANT2 can create NNs that are very specialised; they achieve a very good performance while being relatively small. This can be seen in expe...

The iterative closest point (ICP) algorithm is one of the most popular approaches to shape registration currently in use. At the core of ICP is the computationally-intensive determination of nearest neighbors (NN). As of now there has been no comprehensive analysis of competing search strategies for NN. This paper compares several libraries for nearest-neighbor search (NNS) on both simulated an...

The increasing demand for neural networks (NNs) being employed on embedded devices has led to plenty of research investigating methods for training low precision NNs. While most methods involve a quantization step, we propose a principled Bayesian approach where we first infer a distribution over a discrete weight space from which we subsequently derive hardware-friendly low precision NNs. To t...

AIMS AND OBJECTIVES: Suck development is a challenging hurdle for preterm infants who endure an extensive oxygen history due to respiratory distress syndrome (RDS). The fine structure of the non-nutritive suck (NNS) was studied in preterm infants according to RDS severity. DESIGN AND METHODS: Recordings of NNS were completed cribside in the neonatal intensive care unit (NICU) in 55 preterm infa...

Neural networks (NNs) are computational tools capable of incredible nonlinear functional approximation. Commonly used for time-series prediction, NNs face a scaling problem when large numbers of inputs and outputs are needed. Increasingly more neurons are required for each additional input or output to be computed. Living brains, the inspiration for NNs, exhibit capabilities to process absolute...

This paper proposes a co-evolutionary learning system, i.e., CELS, to design neural network (NN) ensembles. CELS addresses the issue of automatic determination of the number of individual NNs in an ensemble and the exploitation of the interaction between individual NN design and combination. The idea of CELS is to encourage diierent individual NNs in the ensemble to learn diierent parts or aspe...