专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

US20240265243A1 METHOD AND SYSTEM FOR NEURAL NETWORK INFERENCING IN LOGARITHMIC DOMAIN 审中-公开
公开(公告)号：US20240265243A1
公开(公告)日：2024-08-08
申请号：US18422076
申请日：2024-01-25
申请人： Tata Consultancy Services Limited
发明人： Archisman BHOWMICK , Mayank MISHRA , Rekha SINGHAL , Aditya Singh RATHORE
IPC分类号： G06N3/048
CPC分类号： G06N3/048
摘要： This disclosure relates generally to neural network inferencing, and more particularly, to a method and system for neural network inferencing in logarithmic domain. The conventional techniques include training a neural network in logarithmic domain and performing inferencing. This leads to less accuracy, challenge in converting large models and unable to perform optimization. The present disclosure converts a pre-trained neural network into logarithmic domain using a bit manipulation based logarithm number system technique wherein the neural network is pre-trained in real time or in logarithmic domain. The method converts the weights, neural network layers and activation function into logarithmic domain. The method uses a 32-bit integer variable to store a logarithm number which leads to memory efficiency. The disclosed method is used for inferencing of convolutional neural network for natural language processing, image recognition and so on.

2. 发明申请

US20210232971A1 DATA META-MODEL BASED FEATURE VECTOR SET GENERATION FOR TRAINING MACHINE LEARNING MODELS 有权
公开(公告)号：US20210232971A1
公开(公告)日：2021-07-29
申请号：US17160197
申请日：2021-01-27
申请人： Tata Consultancy Services Limited
发明人： Mayank MISHRA , Shruti KUNDE , Sharod ROY CHOUDHURY , Amey PANDIT , Manoj Karunakaran NAMBIAR , Siddharth VERMA , Gautam SHROFF , Pankaj MALHOTRA , Rekha SINGHAL
IPC分类号： G06N20/00 , G06F16/2458 , G06F16/23
摘要： This disclosure relates generally to data meta model and meta file generation for feature engineering and training of machine learning models thereof. Conventional methods do not facilitate appropriate relevant data identification for feature engineering and also do not implement standardization for use of solution across domains. Embodiments of the present disclosure provide systems and methods wherein datasets from various sources/domains are utilized for meta file generation that is based on mapping of the dataset with a data meta model based on the domains, the meta file comprises meta data and information pertaining to action(s) being performed. Further functions are generated using the meta file and the functions are assigned to corresponding data characterized in the meta file. Further functions are invoked to generate feature vector set and machine learning model(s) are trained using the features vector set. Implementation of the generated data meta-model enables re-using of feature engineering code.

3. 发明公开

US20240160949A1 GENERATING META-SUBNETS FOR EFFICIENT MODEL GENERALIZATION IN A MULTI-DISTRIBUTION SCENARIO 审中-公开
公开(公告)号：US20240160949A1
公开(公告)日：2024-05-16
申请号：US18454329
申请日：2023-08-23
申请人： Tata Consultancy Services Limited
发明人： Shruti Kunal KUNDE , Rekha SINGHAL , Varad Anant PIMPALKHUTE
IPC分类号： G06N3/0985
CPC分类号： G06N3/0985
摘要： Technical limitation of conventional Gradient-Based Meta Learners is their inability to adapt to scenarios where input tasks are sampled from multiple distributions. Training multiple models, with one model per distribution adds to the training time owing to increased compute. A method and system for generating meta-subnets for efficient model generalization in a multi-distribution scenario using Binary Mask Perceptron (BMP) technique or a Multi-modal Meta Supermasks (MMSUP) technique is provided. The BMP utilizes an adaptor which determines a binary mask, thus training only those layers which are relevant for given input distribution, leading to improved training accuracy in a cross-domain scenario. The MMSUP, further determines relevant subnets for each input distribution, thus, generalizing well as compared to standard MAML. The BMP and MMSUP, beat Multi-MAML in terms of training time as they train a single model on multiple distributions as opposed to Multi-MAML which trains multiple models.

4. 发明申请

US20210390033A1 ACCELERATING DEVELOPMENT AND DEPLOYMENT OF ENTERPRISE APPLICATIONS IN DATA DRIVEN ENTERPRISE IT SYSTEMS 有权
公开(公告)号：US20210390033A1
公开(公告)日：2021-12-16
申请号：US17345166
申请日：2021-06-11
申请人： Tata Consultancy Services Limited
发明人： Rekha SINGHAL , Gautam SHROFF , Dheeraj CHAHAL , Mayank MISHRA , Shruti KUNDE , Manoj NAMBIAR
IPC分类号： G06F11/36 , G06F9/48 , G06N3/02 , G06K9/62
摘要： This disclosure relates generally to accelerating development and deployment of enterprise applications where the applications involve both data driven and task driven components in data driven enterprise information technology (IT) systems. The disclosed system is capable of determining components of the application that may be task-driven and/or those components which may be data-driven using inputs such as business use case, data sources and requirements specifications. The system is capable of determining the components that may be developed using task-driven and data-drive paradigms and enables migration of components from the task driven paradigm to the data driven paradigm. Also, the system trains a reinforcement learning (RL) model for facilitating migration of the identified components from the task driven paradigm to the data driven paradigm. The system is further capable of integrating the migrated and existing components to accelerate development and deployment an integrated IT application.

5. 发明申请

US20190294977A1 METHOD AND SYSTEM FOR SYSTEM ARCHITECTURE TECHNOLOGY RECOMMENDATION 审中-公开
公开(公告)号：US20190294977A1
公开(公告)日：2019-09-26
申请号：US16359951
申请日：2019-03-20
申请人： Tata Consultancy Services Limited
发明人： Shruti KUNDE , Chetan PHALAK , Rekha SINGHAL , Manoj NAMBIAR
IPC分类号： G06N5/02 , G06N7/00 , G06F16/9035
摘要： The disclosure generally relates to system architectures, and, more particularly, to a method and system for system architecture recommendation. In existing scenario, a solution architect often gets minimum details about requirements, hence struggles to design a system architecture that matches the requirements. The method and system disclosed herein are to provide system recommendation in response to requirements provided as input to the system. The system generates an acyclic dependency graph based on parameters and values extracted from an obtained user input. The system then identifies a reference architectures that matches the requirements, and further selects components that match the architecture requirements. The system further selects technologies considering inter-operability of the technologies. Further, the system generates architecture recommendations for the user, based on the selected components, and technologies. The system can collect user feedback for to the recommendation provided, and can generate rankings to improve future recommendations.

6. 发明公开

US20240062045A1 METHOD AND SYSTEM FOR LATENCY OPTIMIZED HETEROGENEOUS DEPLOYMENT OF CONVOLUTIONAL NEURAL NETWORK 审中-公开
公开(公告)号：US20240062045A1
公开(公告)日：2024-02-22
申请号：US18227061
申请日：2023-07-27
申请人： Tata Consultancy Services Limited
发明人： Nupur SUMEET , Manoj Karunakaran NAMBIAR , Rekha SINGHAL , Karan RAWAT
IPC分类号： G06N3/0464
CPC分类号： G06N3/0464
摘要： This disclosure relates generally to a method and system for latency optimized heterogeneous deployment of convolutional neural network (CNN). State-of-the-art methods for optimal deployment of convolutional neural network provide a reasonable accuracy. However, for unseen networks the same level of accuracy is not attained. The disclosed method provides an automated and unified framework for the convolutional neural network (CNN) that optimally partitions the CNN and maps these partitions to hardware accelerators yielding a latency optimized deployment configuration. The method provides an optimal partitioning of the CNN for deployment on heterogeneous hardware platforms by searching network partition and hardware pair optimized for latency while including communication cost between hardware. The method employs performance model-based optimization algorithm to optimally deploy components of a deep learning pipeline across right heterogeneous hardware for high performance.

7. 发明申请

US20170169336A1 SYSTEMS AND METHODS FOR GENERATING PERFORMANCE PREDICTION MODEL AND ESTIMATING EXECUTION TIME FOR APPLICATIONS 审中-公开
公开(公告)号：US20170169336A1
公开(公告)日：2017-06-15
申请号：US15070979
申请日：2016-03-15
申请人： Tata Consultancy Services Limited
发明人： Rekha SINGHAL , Amit Sangroya
IPC分类号： G06N5/02 , G06F17/30
摘要： Systems and methods for generating performance prediction model and estimating execution time for applications is provided. The system executes synthetic benchmarks for a first dataset on a first cluster. Each synthetic benchmark includes a MapReduce (MR) job. The system further extracts sensitive parameters for each sub-phase of the MR job, generates a linear regression prediction model for each sub-phase to obtain one or more linear regression prediction models, based on which the system further generates a performance prediction model to be utilized for predicting, using the sensitive parameters, a Hive query execution time of a DAG of one or more MR jobs executed on a second dataset on a second cluster, wherein the first cluster that includes the first dataset is smaller compared to the second cluster that includes the second dataset.

8. 发明申请

US20160140171A1 METHOD AND SYSTEM FOR EFFICIENT PERFORMANCE PREDICTION OF STRUCTURED QUERY FOR BIG DATA 审中-公开
标题翻译：用于大数据的结构查询的有效性能预测的方法和系统
公开(公告)号：US20160140171A1
公开(公告)日：2016-05-19
申请号：US14663647
申请日：2015-03-20
申请人： Tata Consultancy Services Limited
发明人： Rekha SINGHAL
IPC分类号： G06F17/30
CPC分类号： G06F17/30442 , G06F17/30477
摘要： Disclosed is a system for predicting an Elapsed Response Time (ERT) of a query to be executed in a production database. The system includes a database emulator module for creating an emulated database based on empty schema derived by extrapolating statistical information from the development environment. The system also includes an execution plan generation module for generating a query execution plan of the query. The system further includes a query classifying module for classifying each sub-query based on the operational parameters into at least one of a full table scan, a primary index scan, a fast index scan and a non-unique index scan. The system also includes a time determination module for executing each sub-query on the emulated database to determine an Input Output (IO) access time and an operator time. Moreover, the system includes an ERT prediction module for predicting the ERT of the query to be executed in the production database based on the IO access time, the operator time, and a network time.
摘要翻译：公开了一种用于预测要在生产数据库中执行的查询的经过响应时间（ERT）的系统。该系统包括一个数据库仿真器模块，用于基于通过从开发环境推断统计信息而导出的空模式创建仿真数据库。该系统还包括用于生成查询的查询执行计划的执行计划生成模块。该系统还包括一个查询分类模块，用于根据操作参数将每个子查询分类为全表扫描，主索引扫描，快速索引扫描和非唯一索引扫描中的至少一个。该系统还包括用于执行仿真数据库上的每个子查询的时间确定模块，以确定输入输出（IO）访问时间和操作者时间。此外，该系统包括ERT预测模块，用于基于IO访问时间，运营商时间和网络时间来预测在生产数据库中执行的查询的ERT。

9. 发明公开

US20230409967A1 TRAINING LARGE DL MODELS VIA SERVERLESS ARCHITECTURE USING CLOUD STORAGE SERVICES-BASED COMMUNICATION CHANNEL 审中-公开
公开(公告)号：US20230409967A1
公开(公告)日：2023-12-21
申请号：US18140219
申请日：2023-04-27
申请人： Tata Consultancy Services Limited
发明人： Dheeraj CHAHAL , Surya Chaitanya Venkata PALEPU , Mayank MISHRA , Ravi Kumar SINGH , Rekha SINGHAL
IPC分类号： G06N20/00
CPC分类号： G06N20/00
摘要： State of the art methods require size of DL model, or its gradients be less than maximum data item size of storage used as a communication channel for model training with serverless platform. Embodiments of the present disclosure provide method and system for training large DL models via serverless architecture using communication channel when the gradients are larger than maximum size of one data item allowed by the channel. Gradients that are generated by each worker during current training instance, are chunked into segments and stored in the communication channel. Corresponding segments of each worker are aggregated by aggregators and stored back. Each of the aggregated corresponding segments are read by each worker to generate an aggregated model to be used during successive training instance. Optimization techniques are used for reading-from and writing-to the channel resulting in significant improvement in performance and cost of training.

10. 发明申请

US20200090056A1 SYSTEMS AND METHODS FOR REAL TIME CONFIGURABLE RECOMMENDATION USING USER DATA 审中-公开
公开(公告)号：US20200090056A1
公开(公告)日：2020-03-19
申请号：US16361778
申请日：2019-03-22
申请人： Tata Consultancy Services Limited
发明人： Rekha SINGHAL , Gautam SHROFF , Vartika TEWARI , Sanket KADARKAR , Siddharth VERMA , Sharod Roy CHOUDHURY , Lovekesh VIG , Rupinder VIRK
IPC分类号： G06N5/04 , G06N20/20 , G06F16/901 , G06F16/908 , G06N3/04 , G06K9/62
摘要： Business to Consumer (B2C) systems face a challenge of engaging users since offers are created using static rules generated using clustering on large transactional data generated over a period of time. Moreover, the offer creation and assignment engine is disjoint to the transactional system which led to significant gap between history used to create offers and current activity of users. Systems and methods of the present disclosure provide a meta-model based configurable auto-tunable recommendation model generated by ensembling optimized machine learning and deep learning models to predict a user's likelihood to take an offer and deployed in real time. Furthermore, the offer given to the user is based on a current context derived from the user's recent behavior that makes the offer relevant and increases probability of conversion of the offer to a sale. The system achieves low recommendation latency and scalable high throughput by virtue of the architecture used.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式