Abstract: Large training times incurred during the process of self-learning of ML models in digital twins are debilitating and can adversely affect the functioning of industrial plants. Embodiments of the present disclosure provide a method and system for accelerated self-learning using application agnostic meta learner trained using optimal set of meta features selected from classification meta features, regression meta features, and domain meta features based on a domain-meta-feature-taxonomy created for a plurality of industrial plants across a plurality of domains. Optimal feature selection is enabled using ML, DL that provides static feature selection, while Q-learning based approach is disclosed that enables dynamic feature selection. Q-learning based approach has two implementations, static and dynamic reward.

Abstract: 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.

Abstract: Recent techniques for workload characterization of an application to be executed in a serverless execution environment or cloud are based on benchmark-approximation. Multiple microbenchmarks are run against the multiple VM configurations and a score is calculated which is used for mapping futuristic workloads to the appropriate configuration. Embodiments herein disclose method and system for workload characterization-based capacity planning of an actual application running on-premise with different configurations of the same machine and providing a cost-effective and high-performance serverless execution environment. Resource demand of each API in the application workflow is evaluated. Based on the resource demand of each API, a mapping is performed to the serverless platform on cloud. Additionally, characterization of threads within each API is performed and each thread is mapped to a serverless instance based on its resource requirements.

Abstract: Existing model deployment approaches have the disadvantage that they do not consider feasibility of cloud instances for hosting a given LLM model. Embodiments disclosed herein provide a method and system for deployment of LLMs in a plurality of cloud instances. The system checks feasibility of the plurality of cloud instances for hosting an LLM, based on size of the LLM and storage space in each of the cloud instances. Further, a latency value for a plurality of batch sizes is determined for a plurality of LLM-accelerator pairs, in each of the plurality of cloud instances identified as feasible based on the feasibility check, using a performance model. Furthermore, a recommendation of one of the plurality of cloud instances identified as feasible is generated, based on the determined latency, a measured cost of deployment, a user workload, an application type, a plurality of latency constraints, and an evaluated performance.

Abstract: Data processing code in machine learning pipelines is primarily done using data frame APIs provided by Pandas and similar libraries. Though, these libraries are easy to use, their temporal performance is worse than similar code written using NumPy or other high-performance libraries. Embodiments herein provide a system and method for acceleration of slower data processing code in machine learning pipelines by automatically generating an accelerated data processing code. Initially, a code is received and pre-processed based on a predefined format to get a standardized code. Further, system identifies code statements having operations that to be performed on a data frame, and an ordered list of data frame columns to generate a filtered dictionary code. Further, a data processing representation is generated using filtering dictionary code and ordered list of data frame columns. Finally, an accelerated data processing code is recommended based on the data processing representation.

Abstract: Proliferation of edge devices has significantly advanced technologies in sectors such as autonomous driving and surveillance. However, deploying machine learning models on these resource-constrained devices presents challenges including scalability and managing unpredictable workloads thereby affecting real-time performance in edge-only environments. The present disclosure discloses a method and system for workload deployment in a content guided and service level agreement (SLA) aware edge-cloud architecture. In the present disclosure, a camera feed content-guided load balancing technique is provided that dynamically manages workloads between edge and cloud. Features are extracted from an incoming camera feed to perform load-balancing process efficiently. The load balancer determines a maximum number of concurrent feeds for processing at the edge, with the remaining feeds handled by the cloud based on content of the incoming camera feed.

Abstract: 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.

Abstract: Heterogeneous cloud storage services offered by different cloud service providers have unique deliverable performance. One key challenge is to find the maximum achievable data transfer rate from one cloud service to another. The disclosure herein generally relates to cloud computing, and, more particularly, to a method and system for parameter tuning in cloud network. The system obtains optimum value of parameters of a source cloud and a destination cloud in a cloud pair, by performing a parameter tuning. The optimum value of parameters and corresponding data transfer rate is used as a training data to generate a data model. The data model processes real-time information with respect to cloud pairs, and predicts corresponding data transfer rate.

Abstract: The disclosure generally relates to an FPGA-based online 3D bin packing. Online 3D bin packing is the process of packing boxes into larger bins-Long Distance Containers (LDCs) such that the space inside each LDC is used to the maximum extent. The use of deep reinforcement learning (Deep RL) for this process is effective and popular. However, since the existing processor-based implementations are limited by Von-Neumann architecture and take a long time to evaluate each alignment for a box, only a few potential alignments are considered, resulting in sub-optimal packing efficiency. This disclosure describes an architecture for bin packing which leverages pipelining and parallel processing on FPGA for faster and exhaustive evaluation of all alignments for each box resulting in increased efficiency. In addition, a suitable generic purpose processor is employed to train the neural network within the algorithm to make the disclosed techniques computationally light, faster and efficient.

Abstract: The disclosure relates generally to methods and systems for multi-objective workflow scheduling to serverless architecture in a multi-cloud environment. Generating an optimal mapping scheme for heterogeneous tasks of the complex task workflow in the multi-cloud environment is always a challenge. The present disclosure make use of the serverless platforms in conjunction with the storage services for the optimal mapping of the task workflows to the multi-cloud environment using the particle swarm optimization (PSO) algorithm. In the present disclosure, each of the tasks of the application are characterized to determine one or more compute requirements, and one or more input/output (I/O) requirements. Furthermore, a compute capacity of each of the plurality of serverless computing instances, and bandwidth measurements are determined. Then, the optimized task workflow is generated, using the PSO technique by minimizing a multi-objective optimization function.

Abstract: High-performance deployment of DNN recommendation models heavily rely on embedding tables, and their performance bottleneck lies in the latency of embedding access. To optimize the deployment of RMs, the method and system is disclosed, which leverages heterogeneous memory types on FPGAs to improve the overall performance by maximizing the availability of frequently accessed data in faster memory. The system, using a optimizer dynamically allocates table partitions of the embedding tables based on history of input access history. A pre-optimizer block disclosed determines whether smaller tables should be partitioned or placed entirely in smaller memories, improving overall efficiency. The performance of RM is improved with improvement in average embedding fetch latency and effectively inference latency via modified Round Trip computation.

Abstract: Existing approaches for distributing data processing across nodes in a distributed computing environment, based on left over memory with each node, have the disadvantage that they require block placement to be done by a user. Embodiments disclosed herein provide a method and system for optimal placement of transformer model blocks across worker nodes. The system determines left over memory at each of a plurality of worker nodes. Further, based on the left over memory and size of transformer model blocks, the system prioritizes the worker nodes, and accordingly allocates the transformer blocks across the worker nodes.

Abstract: In remote sensing, hyperspectral (HS) images are acquired to study earth's surface. Processing of HS images through neural networks demands significant computational resources for both training and inference phases. The present disclosure addresses the unresolved problem of the conventional methods for reducing dimensions in hyper-spectral data and accelerating the training and inference of a model by applying approximate computing techniques. The approximate computing techniques leverage physical properties of a reflectance spectra. This makes the HS images interpretable across various applications. In the present disclosure, three reflexivity-based approximate computing techniques namely R-Hop(K), R-Top(N), and R-Proximity(N) are implemented. These reflexivity-based approximate computing techniques use spectral clustering methods that rely on reflectance values to capture inherent characteristics from hyperspectral images across diverse domains.

Abstract: Multi-object tracking (MOT) in video sequences plays a critical role in various computer vision applications. The primary objective of MOT is to accurately localize and track objects across consecutive frames. However, existing MOT approaches often suffer from computational limitations and low frame rates in commodity machines, which hinders real-time performance. Present disclosure provides method and system for performing content aware multi-object tracking. The system first classifies video into slow and fast moving object content videos depending on features of objects to be tracked in frames. Then, system applies a computationally intensive deep sort algorithm to perform tracking of objects by selectively skipping frames.

Abstract: High-performance deployment of DNN recommendation models heavily rely on embedding tables, and their performance bottleneck lies in the latency of embedding access. To optimize the deployment of RMs, the method and system is disclosed, which leverages heterogeneous memory types on FPGAs to improve the overall performance by maximizing the availability of frequently accessed data in faster memory. The system, using a optimizer dynamically allocates table partitions of the embedding tables based on history of input access history. A pre-optimizer block disclosed determines whether smaller tables should be partitioned or placed entirely in smaller memories, improving overall efficiency. The performance of RM is improved with improvement in average embedding fetch latency and effectively inference latency via modified Round Trip computation.

Abstract: Works in the literature fail to leverage embedding access patterns and memory units' access/storage capabilities, which when combined can yield high-speed heterogeneous systems by dynamically re-organizing embedding tables partitions across hardware during inference. A method and system for optimal deployment of embeddings tables across heterogeneous memory architecture for high-speed recommendations inference is disclosed, which dynamically partitions and organizes embedding tables across fast memory architectures to reduce access time. Partitions are chosen to take advantage of the past access patterns of those tables to ensure that frequently accessed data is available in the fast memory most of the time. Partition and replication is used to co-optimize memory access time and resources.

Abstract: The disclosure addresses problems associated with a systematic integration of multi-modal data for effective training, and handling of large volume of data because of high resolution of the multiple modalities. Embodiments herein provide a method and a system for a distributed training of a multi-modal data fusion transformer. Herein, a distributed training approach called a Distributed Architecture for Fusion-Transformer Training Acceleration (DAFTA) is proposed for processing large multimodal remote sensing data. DAFTA is enabled to handle any combination of remote sensing modalities. Additionally, similarity of feature space is leveraged to optimize the training process and to achieve the training with reduced data set which is equivalent to a complete data set. The proposed approach provides a systematic and efficient method for managing large sensing data and enables accurate and timely insights for various applications.

Abstract: 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.

Abstract: The present disclosure provides a scalable acceleration of data processing in Machine Learning pipeline which is unavailable in conventional methods. Initially, the system receives a dataset and a data processing code. A plurality of sample datasets are obtained based on the received dataset using a sampling technique. A plurality of performance parameters corresponding to each of the plurality of sample datasets are obtained based on the data processing code using a profiling technique. A plurality of scalable performance parameters corresponding to each of a plurality of larger datasets are predicted based on the plurality of performance parameters and the data processing code using a curve fitting technique. Simultaneously, a plurality of anti-patterns are located in the data processing code using a pattern matching technique.

Abstract: Cloud and Fog computing are complementary technologies used for complex Internet of Things (IoT) based deployment of applications. With an increase in the number of internet-connected devices, the volume of data generated and processed at higher speeds has increased substantially. Serving a large amount of data and workloads for predictive decisions in real-time using fog computing without Service-Level Objective (SLO) violation is a challenge. Present disclosure provides systems and method for inference management wherein a suitable execution workflow is automatically generated to execute machine learning (ML)/deep learning (DL) inference requests using fog with various type of instances (e.g., Function-as-a-Service (FaaS) instance, Machine Learning-as-a-service (MLaaS) instance, and the like) provided by cloud vendors/platforms. Generated workflow minimizes the cost of deployment as well as SLO violations.