Co-Training for Visual Object Recognition Based on Self-Supervised Models Using a Cross-Entropy Regularization

Automatic recognition of visual objects using a deep learning approach has been successfully applied to multiple areas. However, deep learning techniques require a large amount of labeled data, which is usually expensive to obtain. An alternative is to use semi-supervised models, such as co-training, where multiple complementary views are combined using a small amount of labeled data. A simple way to associate views to visual objects is through the application of a degree of rotation or a type of filter. In this work, we propose a co-training model for visual object recognition using deep neural networks by adding layers of self-supervised neural networks as intermediate inputs to the views, where the views are diversified through the cross-entropy regularization of their outputs. Since the model merges the concepts of co-training and self-supervised learning by considering the differentiation of outputs, we called it Differential Self-Supervised Co-Training (DSSCo-Training). This paper presents some experiments using the DSSCo-Training model to well-known image datasets such as MNIST, CIFAR-100, and SVHN. The results indicate that the proposed model is competitive with the state-of-art models and shows an average relative improvement of 5% in accuracy for several datasets, despite its greater simplicity with respect to more recent approaches.     

Local linear convergence analysis of Primal–Dual splitting methods

In this paper, we study the local linear convergence properties of a versatile class of Primal–Dual splitting methods for minimizing composite non-smooth convex optimization problems. Under the assumption that the non-smooth components of the problem are partly smooth relative to smooth manifolds, we present a unified local convergence analysis framework for these methods. More precisely, in our framework, we first show that (i) the sequences generated by Primal–Dual splitting methods identify a pair of primal and dual smooth manifolds in a finite number of iterations, and then (ii) enter a local linear convergence regime, which is characterized based on the structure of the underlying active smooth manifolds. We also show how our results for Primal–Dual splitting can be specialized to cover existing ones on Forward–Backward splitting and Douglas–Rachford splitting/ADMM (alternating direction methods of multipliers). Moreover, based on these obtained local convergence analysis result, several practical acceleration techniques are discussed. To exemplify the usefulness of the obtained result, we consider several concrete numerical experiments arising from fields including signal/image processing, inverse problems and machine learning. The demonstration not only verifies the local linear convergence behaviour of Primal–Dual splitting methods, but also the insights on how to accelerate them in practice.     

Enantioselective analysis of venlafaxine and its active metabolites: A review on the separation methodologies

Venlafaxine (VFX) is a serotonin and norepinephrine reuptake inhibitor chiral drug used in therapy as an antidepressant in the form of a racemate consisting of R‐ and S‐VFX. The two enantiomers of VFX exhibit different pharmacological activities: R‐VFX inhibits both norepinephrine and serotonin synaptic reuptake, whereas S‐VFX inhibits only the serotonin one. R‐ and S‐VFX are metabolized in the liver to the respective R‐ and S‐O‐desmethylvenlafaxine (ODVFX), R‐ and S‐N‐desmethylvenlafaxine (NDVFX), and R‐ and S‐N,O‐didesmethylvenlafaxine (NODVFX). The pharmacological profile of ODVFX is close to that of VFX, whereas the other two chiral metabolites (NDVFX and NODVFX) have lower affinity for the receptor sites. The pharmacokinetics of the VFX enantiomers appear stereoselective, including the metabolism process. In the past 20 years, several studies describing the enantioselective analysis of R‐ and S‐VFX in pharmaceutical formulations and its chiral metabolites in biological matrices were published. These methods encompass liquid chromatography coupled with UV detection, mass spectrometry, or tandem mass spectrometry, and capillary electrophoresis. This paper reviews the published methods used for the determination of the individual enantiomers of VFX and its chiral metabolites in different matrices.     

Modeling of Atmospheric-Pressure Dielectric Barrier Discharges in Argon with Small Admixtures of Tetramethylsilane

Plasma Chemistry and Plasma Processing - A time-dependent, spatially one-dimensional fluid-Poisson model is applied to analyze the impact of small amounts of tetramethylsilane (TMS) as precursor on...     

Parametric instability of a magnetic pendulum in the presence of a vibrating conducting plate

Nonlinear Dynamics - A pendulum with an attached permanent magnet swinging in the vicinity of a conductor is a typical experiment for the demonstration of electromagnetic braking and Lenz’...     

Strategic analysis of the dairy transportation problem

The dairy transportation problem (DTP) consists of determining the best routes to be performed for collecting milk from farms and delivering it to processing plants. We study the particular case of the province of Quebec, where the Fédération des producteurs de lait du Québec is responsible for negotiating the transportation costs on behalf of producers. Several issues are highlighted in the actual process of designing contracts such as using historical data. We propose an approach based on scenario analysis that consists of revising both the steps and the information used to construct the routes. We develop a generalized tabu search algorithm that integrates the different characteristics of the DTP.