Much has been said about the fusion of bio-inspired optimization algorithms and Deep Learning models for several purposes: from the discovery of network topologies and hyper-parametric configurations ...with improved performance for a given task, to the optimization of the model's parameters as a replacement for gradient-based solvers. Indeed, the literature is rich in proposals showcasing the application of assorted nature-inspired approaches for these tasks. In this work we comprehensively review and critically examine contributions made so far based on three axes, each addressing a fundamental question in this research avenue: a) optimization and taxonomy (Why?), including a historical perspective, definitions of optimization problems in Deep Learning, and a taxonomy associated with an in-depth analysis of the literature, b) critical methodological analysis (How?), which together with two case studies, allows us to address learned lessons and recommendations for good practices following the analysis of the literature, and c) challenges and new directions of research (What can be done, and what for?). In summary, three axes - optimization and taxonomy, critical analysis, and challenges - which outline a complete vision of a merger of two technologies drawing up an exciting future for this area of fusion research.
The recognition of coral species based on underwater texture images pose a significant difficulty for machine learning algorithms, due to the three following challenges embedded in the nature of this ...data: 1) datasets do not include information about the global structure of the coral; 2) several species of coral have very similar characteristics; and 3) defining the spatial borders between classes is difficult as many corals tend to appear together in groups. For this reason, the classification of coral species has always required an aid from a domain expert. The objective of this paper is to develop an accurate classification model for coral texture images. Current datasets contain a large number of imbalanced classes, while the images are subject to inter-class variation. We have analyzed 1) several Convolutional Neural Network (CNN) architectures, 2) data augmentation techniques and 3) transfer learning. We have achieved the state-of-the art accuracies using different variations of ResNet on the two current coral texture datasets, EILAT and RSMAS.
There is a growing demand for accurate high-resolution land cover maps in many fields, e.g., in land-use planning and biodiversity conservation. Developing such maps has been performed using ...Object-Based Image Analysis (OBIA) methods, which usually reach good accuracies, but require a high human supervision and the best configuration for one image can hardly be extrapolated to a different image. Recently, the deep learning Convolutional Neural Networks (CNNs) have shown outstanding results in object recognition in the field of computer vision. However, they have not been fully explored yet in land cover mapping for detecting species of high biodiversity conservation interest. This paper analyzes the potential of CNNs-based methods for plant species detection using free high-resolution Google Earth T M images and provides an objective comparison with the state-of-the-art OBIA-methods. We consider as case study the detection of Ziziphus lotus shrubs, which are protected as a priority habitat under the European Union Habitats Directive. According to our results, compared to OBIA-based methods, the proposed CNN-based detection model, in combination with data-augmentation, transfer learning and pre-processing, achieves higher performance with less human intervention and the knowledge it acquires in the first image can be transferred to other images, which makes the detection process very fast. The provided methodology can be systematically reproduced for other species detection.
In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire ...community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
This paper presents a new model for the computation of the insolation in large territories. The main novelty of this work consists in that it reduces significatively the number of necessary ...arithmetic operations, and simplifies the calculations introducing errors that are inferior to the ones imposed by the climate in a territory. In particular, a faster algorithm to compute the horizon at all points of a terrain is provided. This algorithm is also useful for shading and visibility applications. Moreover, parallel computing is introduced into this model using grid computing technology to extend its application to very large territories.
Broadband emission from relativistic outflows (jets) of active galactic nuclei (AGN) and gamma-ray bursts (GRBs) contains valuable information about the nature of the jet itself, and about the ...central engine which launches it. Using special relativistic hydrodynamics and magnetohydronamics simulations we study the dynamics of the jet and its interaction with the surrounding medium. The observational signature of the simulated jets is computed using a radiative transfer code developed specifically for the purpose of computing multi-wavelength, time-dependent, non-thermal emission from astrophysical plasmas. We present results of a series of long-term projects devoted to understanding the dynamics and emission of jets in parsec-scale AGN jets, blazars and the afterglow phase of the GRBs.
Parallel programming is a requirement in the multi-core era. One of the most promising techniques to make parallel programming available for general users is the use of parallel programming patterns. ...Functional pipeline parallelism is a well suited pattern for many emerging applications, such as streaming and "Recognition, Mining and Synthesis" (RMS) workloads. In this paper we develop an analytical model for pipeline parallelism and use it to characterize and optimize two of the PARSEC benchmarks which use the parallel pipeline pattern, ferret and dedup. We identify two scalability limitations: load imbalance and I/O bottlenecks. We address load imbalance using two techniques: parallel pipeline stage collapsing and dynamic scheduling. We implemented these optimizations using Pthreads and the Threading Building Blocks (TBB) libraries. We compare predicted and measured performance of all these implementations on a large scale SMP machine and we note that the work-stealing TBB implementation outperforms all other variants.
This article describes and analyzes the parallelization of the Anisotropic Nonlinear Diffusion (AND) for filtering 3D images. AND is one of the most powerful denoising techniques in the field of ...computer vision. This technique consists in resolving the equation of diffusion tightly coupled with a massive set of eigensystems. Denoising large 3D images in biomedicine and structural cellular biology by AND has a high computational cost. In this work, we propose a portable and efficient parallel implementation of AND based on a hybrid paradigm that combines (1) the message passing model and (2)the shared address space model. The proposed parallel implementation has been evaluated on a cluster of SMPs based on a UMA Uniform Memory access. The evaluation results show that the hybrid model is more suitable for this kind of platforms.