Machine learning on big data: Opportunities and challenges

doi:10.1016/j.neucom.2017.01.026

Paper

Machine learning on big data: Opportunities and challenges

Published May 10, 2017 · Lina Zhou, Shimei Pan, Jianwu Wang

Neurocomputing

Q1 SJR score

797

Citations

14

Influential Citations

Full textSemantic Scholar

Abstract

Abstract hidden due to publisher request; this does not indicate any issues with the research. Click the full text link above to read the abstract and view the original source.

Highly Cited

Study Snapshot

Machine learning on big data offers opportunities for more accurate predictions but also presents challenges like model scalability and distributed computing.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Paper

Machine learning on big data: Opportunities and challenges

Sign up to use Study Snapshot

References

A data-intensive approach for discovering user similarities in social behavioral interactions based on the bayesian network

Our data-intensive approach using Bayesian networks effectively discovers user similarities in social behavioral interactions, aiding in user targeting, product recommendations, and relationship understanding.

Deep Belief Networks for Quantitative Analysis of a Gold Immunochromatographic Strip

Deep belief networks effectively improve the sensitivity and quantitative performance of gold immunochromatographic strip systems by segmenting test and control lines with high accuracy.

Deep learning for visual understanding: A review

Deep learning algorithms have advanced computer vision tasks like image classification, object detection, and human pose estimation, with future trends and challenges in designing and training deep neural networks.

Speed up deep neural network based pedestrian detection by sharing features across multi-scale models

Sharing features across multi-scale deep neural networks significantly reduces computational burden and improves pedestrian detection efficiency with minimal loss of accuracy.

TABLA: A unified template-based framework for accelerating statistical machine learning

TABLA, a template-based framework, generates FPGA-based accelerators for machine learning algorithms, providing significant performance gains over multi-core CPUs and GPUs while requiring less than 50 lines of code.

Citations