1,720,959 research outputs found
Reducing the Computation Load of Convolutional Neural Networks through Gate Classification
No full textReducing the computational load of Convolutional Neural Networks (CNNs) is of utmost importance to allow their execution in computing systems characterized by constraints on computation and energy (e.g., embedded and cyber-physical systems and Internet-of-Things). To address this problem, which has been rarely addressed in the related literature, this paper introduces the Gate-Classification CNNs. The core of this novel family of CNNs is the presence of Gate-Classification layers that allow to incrementally process the input image through the CNN layers and take a decision as soon as 'enough confidence' about the classification is gained, hence not requiring the processing of the whole CNN when not needed. The Gate-Classification CNNs rely on the ability of CNNs to process features characterized by increasing complexity and meaning and, in particular, the Gate-Classification layers allow to select the path within the CNN according to the information content provided by the input image and the processed features. A wide experimental campaign on public-available datasets supports the effectiveness of the proposed solution
Incremental On-Device Tiny Machine Learning
No full textTiny Machine Learning (TML) is a novel research area aiming at designing and developing Machine Learning (ML) techniques meant to be executed on Embedded Systems and Internet-of-Things (IoT) units. Such techniques, which take into account the constraints on computation, memory, and energy characterizing the hardware platform they operate on, exploit approximation and pruning mechanisms to reduce the computational load and the memory demand of Machine and Deep Learning (DL) algorithms. Despite the advancement of the research, TML solutions present in the literature assume that Embedded Systems and IoT units support only the inference of ML and DL algorithms, whereas their training is confined to more-powerful computing units (due to larger computational load and memory demand). This also prevents such pervasive devices from being able to learn in an incremental way directly from the field to improve the accuracy over time or to adapt to new working conditions. The aim of this paper is to address such an open challenge by introducing an incremental algorithm based on transfer learning and k-nearest neighbor to support the on-device learning (and not only the inference) of ML and DL solutions on embedded systems and IoT units. Moreover, the proposed solution is general and can be applied to different application scenarios. Experimental results on image/audio benchmarks and two off-The-shelf hardware platforms show the feasibility and effectiveness of the proposed solution
Learning Convolutional Neural Networks in presence of Concept Drift
No full textDesigning adaptive machine learning systems able to operate in nonstationary conditions, also called concept drift, is a novel and promising research area. Convolutional Neural Networks (CNNs) have not been considered a viable solution for such adaptive systems due to the high computational load and the high number of images they require for the training. This paper introduces an adaptive mechanism for learning CNNs able to operate in presence of concept drift. Such an adaptive mechanism follows an "active approach", where the adaptation is triggered by the detection of a concept drift, and relies on the "transfer learning" paradigm to transfer (part of the) knowledge from the CNN operating before the concept drift to the one operating after. The effectiveness of the proposed solution has been evaluated on two types of CNNs and two real-world image benchmarks
Distributed Deep Convolutional Neural Networks for the Internet-of-Things
No full textSevere constraints on memory and computation characterizing the Internet-of-Things (IoT) units may prevent the execution of Deep Learning (DL)-based solutions, which typically demand large memory and high processing load. In order to support a real-time execution of the considered DL model at the IoT unit level, DL solutions must be designed having in mind constraints on memory and processing capability exposed by the chosen IoT technology. In this paper, we introduce a design methodology aiming at allocating the execution of Convolutional Neural Networks (CNNs) on a distributed IoT application. Such a methodology is formalized as an optimization problem where the latency between the data-gathering phase and the subsequent decision-making one is minimized, within the given constraints on memory and processing load at the units level. The methodology supports multiple sources of data as well as multiple CNNs in execution on the same IoT system allowing the design of CNN-based applications demanding autonomy, low decision-latency, and high Quality-of-Service
A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Service
No full textDeep-learning-as-a-service is a novel and promising computing paradigm aiming at providing machine/deep learning solutions and mechanisms through Cloud-based computing infrastructures. Thanks to its ability to remotely execute and train deep learning models (that typically require high computational loads and memory occupation), such an approach guarantees high performance, scalability, and availability. Unfortunately, such an approach requires to send information to be processed (e.g., signals, images, positions, sounds, videos) to the Cloud, hence having potentially catastrophic-impacts on the privacy of users. This paper introduces a novel distributed architecture for deep-learning-as-a-service that is able to preserve the user sensitive data while providing Cloud-based machine and deep learning services. The proposed architecture, which relies on Homomorphic Encryption that is able to perform operations on encrypted data, has been tailored for Convolutional Neural Networks (CNNs) in the domain of image analysis and implemented through a client-server REST-based approach. Experimental results show the effectiveness of the proposed architecture
A Computational Intelligence Characterization of Solar Magnetograms
No full textSpace Weather (SW) poses a hazard to modern society. SW phenomena depend on the Sun's magnetic field and understanding and forecasting the solar magnetic field is an important research subject. To achieve this goal, in this paper Global Oscillation Network Group (GONG) solar magnetograms 2006-2019 are investigated with different approaches provided by unsupervised and supervised Computational Intelligence techniques. Such techniques were successful at providing insights into the behavior and evolution of the photospheric magnetic field, revealing patterns of activity and their relation with the different phases of the solar cycle. On the one hand, representative prototypes of synoptic maps were found, capturing the variations in homogeneity, intensity and variability of magnetic activity. On the other hand, Convolutional neural networks combined with transfer learning and dimensionality reduction techniques were helpful in providing classification models which accurately predict classes associated to the main stages of the cycle. Such models provide results in good correspondence with the natural classes found in feature spaces and have classification errors concentrated mostly at transition periods of the solar cycles
An energy harvesting solution for computation offloading in Fog Computing networks
Full text linkFog Computing is a promising networking paradigm enabling the nodes at the edge to share computational and storage resources. Being pervasively distributed, Fog Nodes are often battery powered and, for this reason, an efficient energy management should be considered to prolong network lifetime. In this paper, we introduce a smart energy management solution able to exploit information about the predicted harvested and consumed energy by Fog Nodes, equipped with small solar panels. The smart energy management is applied on a cluster based Fog Computing environment where computation offloading operations are performed. In the experimental section the effect of the smart energy management is explored in terms of network lifetime by considering variable battery size and Fog Nodes density in a realistic solar-panel harvesting-model and Fog Nodes setting
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
