Matrix Factorization Techniques for Recommender Systems

OUTPU T 29 OUTPU T 30 OUTPU T 31 OUTPU T 32 OUTPU T 25 OUTPU T 26 OUTPU T 27 OUTPU T 28 OUTPU T 21 OUTPU T 22 OUTPU T 23 OUTPU T 24 OUTPU T 17 OUTPU T 18 OUTPU T 19 OUTPU T 20 OUTPU T 13 OUTPU T 14 OUTPU T 15 OUTPU T 16 OUTPU T 9 OUTPU T 10 OUTPU T 11 OUTPU T 12 OUTPU T 5 OUTPU T 6 OUTPU T 7 OUTPU T 8 OUTPU T 1 OUTPU T 2 OUTPU T 3 OUTPU T 4 29 30 31 32 25 26 27 28 21 22 23 24 17 18 19 20 13 14 15 16 9

A User’s Guide

The Grid 2: Blueprint for a New Computing Infrastructure

Remaining Useful Life (RUL) of a component or a system is defined as the length from the current time to the end of the useful life. Accurate RUL estimation plays a critical role in Prognostics and Health Management(PHM). Data driven approaches for RUL estimation use sensor data and operational data to estimate RUL. Traditional regression based approaches and recent Convolutional Neural Network (CNN) approach use features created from sliding windows to build models. However, sequence information is not fully considered in these approaches. Sequence learning models such as Hidden Markov Models (HMMs) and Recurrent Neural Networks (RNNs) have flaws when modeling sequence information. HMMs are limited to discrete hidden states and are known to have issues when modeling long-term dependencies in the data. RNNs also have issues with long-term dependencies. In this work, we propose a Long Short-Term Memory (LSTM) approach for RUL estimation, which can make full use of the sensor sequence information and expose hidden patterns within sensor data with multiple operating conditions, fault and degradation models. Extensive experiments using three widely adopted Prognostics and Health Management data sets show that LSTM for RUL estimation significantly outperforms traditional approaches for RUL estimation as well as Convolutional Neural Network (CNN).

Long Short-Term Memory Network for Remaining Useful Life estimation

Cloud computing has become a significant technology trend Experts believe cloud computing is currently reshaping information technology and the IT marketplace The advantages of using cloud computing include cost savings, speed to market, access to greater computing resources, high availability, and scalability Handbook of Cloud Computing includes contributions from world experts in the field of cloud computing from academia, research laboratories and private industry This book presents the systems, tools, and services of the leading providers of cloud computing; including Google, Yahoo, Amazon, IBM, and Microsoft The basic concepts of cloud computing and cloud computing applications are also introduced Current and future technologies applied in cloud computing are also discussed Case studies, examples, and exercises are provided throughout Handbook of Cloud Computing is intended for advanced-level students and researchers in computer science and electrical engineering as a reference book This handbook is also beneficial to computer and system infrastructure designers, developers, business managers, entrepreneurs and investors within the cloud computing related industry

Handbook of Cloud Computing

http://www-inf.it-sudparis.eu/~defude/MOPS/cloudfederation.pdf

Cloud federation in a layered service model

Grid broker selection strategies using aggregated resource information

The goal of Grid computing is to integrate the usage of computer resources from cooperating partners in the form of Virtual Organizations (VO). One of its key functions is to match jobs to execution resources efficiently. For interoperability between VOs, this matching operation occurs in resource brokering middleware, commonly referred to as the meta-scheduler or meta-broker. In this paper, we present an approach to a meta-scheduler architecture, combining hierarchical and peer-to-peer models for flexibility and extensibility. Interoperability is further promoted through the introduction of a set of protocols, allowing meta-schedulers to maintain sessions and exchange job and resource state using Web Services. Our architecture also incorporates a resource model that enables an efficient resource matching across multiple Virtual Organizations, especially where the compute resources and state are dynamic. Experiments demonstrate these new functional features across three distributed organizations (BSC, FIU, and IBM), that internally use different job scheduling technologies, computing infrastructure and security mechanisms. Performance evaluations through actual system measurements and simulations provide the insights on the architecture's effectiveness and scalability.

Enabling Interoperability among Grid Meta-Schedulers

Grid computing supports shared access to computing resources from cooperating organizations or institutes in the form of virtual organizations. Resource brokering middleware, commonly known as a meta-scheduler or a resource broker, matches jobs to distributed resources. Recent advances in meta- scheduling capabilities are extended to enable resource matching across multiple virtual organizations. Several architectures have been proposed for interoperating meta-scheduling systems. This paper presents a hybrid approach, combining hierarchical and peer-to-peer architectures for flexibility and extensibility of these systems. A set of protocols are introduced to allow different meta-scheduler instances to communicate over Web Services. Interoperability between three heterogeneous and distributed organizations (namely, BSC, FIU, and IBM), each using different meta-scheduling technologies, is demonstrated under these protocols and resource models.

/pdf/enabling-interoperability-among-meta-schedulers-46hvsrmbus.pdf

Enabling Interoperability among Meta-Schedulers

Matrix factorization (MF) is employed by many popular algorithms, e.g., collaborative filtering. The emerging GPU technology, with massively multicore and high intra-chip memory bandwidth but limited memory capacity, presents an opportunity for accelerating MF much further when appropriately exploiting the GPU architectural characteristics. 
This paper presents cuMF, a CUDA-based matrix factorization library that implements memory-optimized alternate least square (ALS) method to solve very large-scale MF. CuMF uses a variety set of techniques to maximize the performance on either single or multiple GPUs. These techniques include smart access of sparse data leveraging GPU memory hierarchy, using data parallelism in conjunction with model parallelism, minimizing the communication overhead between computing units, and utilizing a novel topology-aware parallel reduction scheme. 
With only a single machine with four Nvidia GPU cards, cuMF can be 6-10 times as fast, and 33-100 times as cost-efficient, compared with the state-of-art distributed CPU solutions. Moreover, this cuMF can solve the largest matrix factorization problem ever reported yet in current literature, while maintaining impressively good performance.

Liana Fong

Papers

Cloud federation in a layered service model

Grid broker selection strategies using aggregated resource information

Enabling Interoperability among Grid Meta-Schedulers

Enabling Interoperability among Meta-Schedulers

Faster and Cheaper: Parallelizing Large-Scale Matrix Factorization on GPUs