Bayesian Optimization for Sparse Neural Networks With Trainable Activation Functions.

In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that can be trained throughout the learning process, as they appear to improve network performance, especially by reducing overfitting. In this paper, we propose a trainable activation function whose parameters need to be estimated.

Non-smooth Bayesian learning for artificial neural networks.

Artificial neural networks (ANNs) are being widely used in supervised machine learning to analyze signals or images for many applications. Using an annotated learning database, one of the main challenges is to optimize the network weights. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively such as gradient-based method, Newton-type method, meta-heuristic method.

Efficacy of orally administered 2-substituted quinolines in experimental murine cutaneous and visceral leishmaniases.

We report in this study the in vivo efficacy of nine 2-substituted quinolines on the Leishmania amazonensis cutaneous infection murine model and on the Leishmania infantum and Leishmania donovani visceral infection murine models. In the case of the L. amazonensis model, quinolines were administered orally at 25 mg/kg twice daily for 15 days.

Preparative separation of quinolines by centrifugal partition chromatography with gradient elution.

Centrifugal partition chromatography has been successfully applied to the separation of 2-alkylquinolines from liquid combinatorial synthesis crude samples. Original gradient elution using the ternary two-phase solvent systems heptane-water-acetonitrile and heptane-acetonitrile-methanol were used to separate them with high purity degrees. Part of the effluent was monitored with evaporative light scattering detection, for direct control, and the collected fractions were analyzed by thin-layer chromatography, GC, nuclear magnetic resonance spectroscopy and MS.