Applying backpropagation neural network in the control of medullary reflex pattern

Dalcin, Bruno Luiz Galluzzi; Cruz, Frederico Alan de Oliveira; Cortez, Célia Martins; Passos, Emmanuel Lopes

doi:10.1063/1.4938913

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use Python with mpi4py package [33] to implement our developed HCMM scheme over Amazon EC2 clusters. To emulate the straggler effects in large-scale systems [34], we inject artificial delays 6 .…”

Section: B Experiments Using Amazon Ec2 Machinesmentioning

confidence: 99%

Coded Computation Over Heterogeneous Clusters

Reisizadeh

Prakash

Pedarsani

et al. 2019

IEEE Trans. Inform. Theory

178

View full text Add to dashboard Cite

In large-scale distributed computing clusters, such as Amazon EC2, there are several types of "system noise" that can result in major degradation of performance: system failures, bottlenecks due to limited communication bandwidth, latency due to straggler nodes, etc. On the other hand, these systems enjoy abundance of redundancy -a vast number of computing nodes and large storage capacity. There have been recent results that demonstrate the impact of coding for efficient utilization of computation and storage redundancy to alleviate the effect of stragglers and communication bottlenecks in homogeneous clusters. In this paper, we focus on general heterogeneous distributed computing clusters consisting of a variety of computing machines with different capabilities. We propose a coding framework for speeding up distributed computing in heterogeneous clusters by trading redundancy for reducing the latency of computation. In particular, we propose Heterogeneous Coded Matrix Multiplication (HCMM) algorithm for performing distributed matrix multiplication over heterogeneous clusters that is provably asymptotically optimal for a broad class of processing time distributions. Moreover, we show that HCMM is unboundedly faster than any uncoded scheme that partitions the total work load among the workers. To demonstrate how the proposed HCMM scheme can be applied in practice, we provide results from numerical studies and Amazon EC2 experiments comparing HCMM with three benchmark load allocation schemes -Uniform Uncoded, Load-balanced Uncoded, and Uniform Coded. In particular, in our numerical studies, HCMM achieves speedups of up to 73%, 56% and 42% respectively over the three benchmark schemes mentioned above. Furthermore, we carry out experiments over Amazon EC2 clusters and demonstrate how HCMM can be combined with rateless codes with nearly linear decoding complexity. In particular, we show that HCMM combined with the Luby transform (LT) codes can significantly reduce the overall execution time. HCMM is found to be up to 61%, 46% and 36% faster than the aforementioned three benchmark schemes, respectively. Additionally, we provide a generalization to the problem of optimal load allocation in heterogeneous settings, where we take into account the monetary costs associated with distributed computing clusters. We argue that HCMM is asymptotically optimal for budget-constrained scenarios as well. In particular, we characterize the minimum possible expected cost associated with a computation task over a given cluster of machines. Furthermore, we develop a heuristic algorithm for (HCMM) load allocation for the distributed implementation of budget-limited computation tasks.

show abstract

Section: B Experiments Using Amazon Ec2 Machinesmentioning

confidence: 99%

Coded Computation Over Heterogeneous Clusters

Reisizadeh

Prakash

Pedarsani

et al. 2019

IEEE Trans. Inform. Theory

178

View full text Add to dashboard Cite

show abstract

“…In equation ( 1), behavioural intention is taken as a function of efort expectancy (EE), facilitating conditions (FC), hedonic motivation (HM), and social infuence (SI). Tis is a standard procedure in line with the guidelines established by Cortez et al [126] for constructing a neural network model. Figure 5 shows the artifcial neural network (ANN) model.…”

Section: Deep Learning-based Artifcial Neural Network Analysismentioning

confidence: 99%

Predictors of Economics Students’ Behavioural Intention to Use Tablets: A Two-Staged Structural Equation Modelling–Artificial Neural Network Approach

Yidana

Arthur

Kaku

et al. 2023

Mobile Information Systems

View full text Add to dashboard Cite

The government of Ghana, as part of its digitisation agenda, intends to provide all senior high school students in Ghana with tablets that are loaded with textbooks and other educational materials for their studies. This initiative is flaunted as one of the game-changing development that is yet to happen in the country. This study employed a modified unified theory of acceptance and use of technology model to examine Economics students’ behavioural intention to use tablets for learning. The study was quantitative research with a focus on a descriptive cross-sectional survey design. A total of 354 senior high school Economics students were selected for the study. A five-point Likert scale instrument was adapted as the data collection instrument for the study. A two-staged partial least square structural equation modelling–artificial neural network approach was used to analyse the data. The results revealed that effort expectancy, facilitating condition, social influence, and hedonic motivation had a significant positive influence on Economics students’ behavioural intention to use tablets for learning. However, habit and performance expectancy had no significant influence on Economics students’ behavioural intentions. Therefore, it was recommended that the implementation of the student-tablet policy should be hinged on social influence, effort expectancy, facilitating condition, and hedonic motivation (the student’s motivation) to use tablets due to internal satisfaction.

show abstract

“…Users can find answers to popular and even niche questions on forums. 81 Second, the Python ecosystem is rich in a variety of add-on packages for efficient numerical computing [82][83][84] , image processing 85,86 , scientific analysis 87 , machine-learning 88 , deep-learning [89][90][91] , file-handling 92 , graphical user interfaces (GUI) 93 , graphical processing unit (GPU) computing 94 , parallel computing [95][96][97][98] , and data visualization 99,100 that dramatically simplify and shrink the time necessary to develop code. Once the USID HDF5 file is generated, the user has access to numerous analysis, visualization, and processing routines in Pycroscopy.…”

Section: Softwarementioning

confidence: 99%

USID and Pycroscopy – Open Source Frameworks for Storing and Analyzing Imaging and Spectroscopy Data

Somnath¹,

Smith

Laanait³

et al. 2019

Microsc Microanal

View full text Add to dashboard Cite

Materials science is undergoing profound changes due to advances in characterization instrumentation that have resulted in an explosion of data in terms of volume, velocity, variety and complexity. Harnessing these data for scientific research requires an evolution of the associated computing and data infrastructure, bridging scientific instrumentation with super-and cloudcomputing. Here, we describe Universal Spectroscopy and Imaging Data (USID), a data model capable of representing data from most common instruments, modalities, dimensionalities, and sizes. We pair this schema with the hierarchical data file format (HDF5) to maximize compatibility, exchangeability, traceability, and reproducibility. We discuss a family of community-driven, open-source, and free python software packages for storing, processing and visualizing data. The first is pyUSID which provides the tools to read and write USID HDF5 files in addition to a scalable framework for parallelizing data analysis. The second is Pycroscopy, which provides algorithms for scientific analysis of nanoscale imaging and spectroscopy modalities and is built on top of pyUSID and USID. The instrument-agnostic nature of USID facilitates the development of analysis code independent of instrumentation and task in Pycroscopy which in turn can bring scientific communities together and break down barriers in the age of openscience. The interested reader is encouraged to be a part of this ongoing community-driven effort to collectively accelerate materials research and discovery through the realms of big data.

show abstract

Applying backpropagation neural network in the control of medullary reflex pattern

Cited by 6 publications

References 12 publications

Coded Computation Over Heterogeneous Clusters

Coded Computation Over Heterogeneous Clusters

Predictors of Economics Students’ Behavioural Intention to Use Tablets: A Two-Staged Structural Equation Modelling–Artificial Neural Network Approach

USID and Pycroscopy – Open Source Frameworks for Storing and Analyzing Imaging and Spectroscopy Data

Contact Info

Product

Resources

About