Performance prediction of paging workloads using lightweight tracing

Burton, A.N.

doi:10.1109/ipdps.2003.1213499

Cited by 1 publication

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Small-scale classification datasets. Following the commonly used training settings, for Connect4 (Burton & Kelly, 2006) and Covertype (Gama et al, 2003) datasets, we randomly take 50 K and 300 K samples for training, and the rest patterns for testing.…”

Section: Resultsmentioning

confidence: 99%

“…However, as for the input dimension, the dimensionality of the input layer is determined based on the processing dataset. For example, for Connect4 (Burton & Kelly, 2006) dataset, the input feature of each pattern is 126. Thus, the input layer dimension for DCNet on Connect4 set is 1 × 1 × 126 (The input size is 1 × 1 and the input channel is 126).…”

Section: Purposesmentioning

confidence: 99%

See 1 more Smart Citation

Deconvolution-and-convolution Networks

Yang,

Zhang,

et al. 2021

Preprint

View full text Add to dashboard Cite

2D Convolutional neural network (CNN) has arguably become the de facto standard for computer vision tasks. Recent findings, however, suggest that CNN may not be the best option for 1D pattern recognition, especially for datasets with over 1 M training samples, e.g., existing CNN-based methods for 1D signals are highly reliant on human pre-processing. Common practices include utilizing discrete Fourier transform (DFT) to reconstruct 1D signal into 2D array. To add to extant knowledge, in this paper, a novel 1D data processing algorithm is proposed for 1D big data analysis through learning a deep deconvolutional-convolutional network. Rather than resorting to human-based techniques, we employed deconvolution layers to convert 1 D signals into 2D data. On top of the deconvolution model, the data was identified by a 2D CNN. Compared with the existing 1D signal processing algorithms, DCNet boasts the advantages of less human-made inference and higher generalization performance. Our experimental results from a varying number of training patterns (50 K to 11 M ) from classification and regression demonstrate the desirability of our new approach.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Purposesmentioning

confidence: 99%