欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对受限玻尔兹曼机（RBM）面对大数据时存在模型训练缓慢的问题，设计了基于 Hadoop 的 RBM 云计算实现方法。针对 RBM 训练方法，改进了 Hadoop 任务消息通信机制以适应模型迭代周期短的特点；设计了MapReduce 框架，包括 Map 端实现吉布斯采样，Reduce 端完成参数更新；依据 Hadoop 任务组合方式，将 RBM 的训练应用于深度玻尔兹曼机（DBM）中。通过手写数字识别实验证明，该计算方法在大规模数据条件下能够有效加速 RBM 训练，且适应于深度学习模型的学习。
英文摘要：
To resolve the slow training of Restricted Boltzmann Machine for handling large data the realization of RBM training based on cloud platform Hadoop is designed.In view of the training method of RBM Hadoop tasks message mechanism was improved to suit RBM′s short iteration cycle MapReduce framework was designed including Map function implemented Gibbs sampling and Reduce function completed parameter update based on Hadoop task combinations RBM′s cloud training was used in Deep Boltz？mann Machine′s training.The handwritten numeral recognition experiments show that this cloud training method can accelerate RBM training effective under large？scale data condition and work well in deep learning model training.
同期刊论文项目
同项目期刊论文
Joint systematic error estimation algorithm for radar and automatic dependent surveillance broadcast
Data Reduction with Quantization Constraints for Decentralized Estimation in Wireless Sensor Network
A New Noise-compensated Estimation Scheme for Multichannel Autoregressive Signals from Noisy Observa
Dual-Decomposition Approach for Distributed Optimization in Wireless Sensor Networks, Wireless Algor
Adaptive range-spread target detection based on modified generalised likelihood ratio test in non-Ga
Diffusion-based EM Algorithm for Distributed Estimation of Gaussian Mixtures in Wireless Sensor Netw
Robust Distributed Fusion for System with Randomly Uncertain Sensor Estimation Error Cross-Covarianc
期刊信息
位置：