Abstract: Embodiments of the present disclosure provide a method and system for co-operative and cascaded inference on the edge device using an integrated Deep Learning (DL) model for object detection and localization, which comprises a strong classifier trained on largely available datasets and a weak localizer trained on scarcely available datasets, and work in coordination to first detect object (fire) in every input frame using the classifier, and then trigger a localizer only for the frames that are classified as fire frames. The classifier and the localizer of the integrated DL model are jointly trained using Multitask Learning approach. Works in literature hardly address the technical challenge of embedding such integrated DL model to be deployed on edge devices. The method provides an optimal hardware software partitioning approach for components or segments of the integrated DL model which achieves a tradeoff between latency and accuracy in object classification and localization.

Abstract: This disclosure relates generally to method and system for jointly pruning and hardware acceleration of pre-trained deep learning models. The present disclosure enables pruning a plurality of DNN models layers using an optimal pruning ratio. The method processes a pruning request to transform the plurality of DNN models and the plurality of hardware accelerators into a plurality of pruned hardware accelerated DNN models based on at least one user option. The first pruning search option executes a hardware pruning search technique to perform search on each DNN model and each processor based on at least one of a performance indicator and an optimal pruning ratio. The second pruning search option executes an optimal pruning search technique, to perform search on each layer with corresponding pruning ratio.

Abstract: State of art techniques existing method refer to handling multiple objectives such as accuracy and latency. However, the reward functions are static and not tunable at user end. Further, for NN search with hardware constraints, approaches combine various techniques such as Reinforcement learning, Evolutionary Algorithm (EA) etc., however hardly any work attempts to disclose combining different NAS approaches in unison to reduce the search space of other. Embodiments of the present disclosure provide a method and system for automated creation of tiny Deep Learning (DL) models to be deployed on a platform having a set of hardware constraints. The method performs a coarse-grained search using a Fast EA NAS model and then utilizes a fine-grained search to identify customized and optimized tiny model. The coarse-grained search and the fine-grained search performed by agents based on a weighted multi-objective reward function, which are tunable at user end.

Abstract: Automatic speech recognition techniques are implemented in resource constrained devices such as edge devices in internet of things where on-device speech recognition is required for low latency and privacy preservation. Existing neural network models for speech recognition have a large size and are not suitable for deployment in such devices. The present disclosure provides an architecture of a size constrained neural network and a method of training the size constrained neural network. The architecture of the size constrained neural network provides a way of increasing or decreasing number of feature blocks to achieve an accuracy-model size trade off. The method of training the size constrained neural network comprises creating a training dataset with short utterances and training the size constrained neural network with the training dataset to learn short term dependencies in the utterances. The trained size constrained neural network model is suitable for deployment in resource constrained devices.

Abstract: Embodiments of the present disclosure provide a method and system for co-operative and cascaded inference on the edge device using an integrated Deep Learning (DL) model for object detection and localization, which comprises a strong classifier trained on largely available datasets and a weak localizer trained on scarcely available datasets, and work in coordination to first detect object (fire) in every input frame using the classifier, and then trigger a localizer only for the frames that are classified as fire frames. The classifier and the localizer of the integrated DL model are jointly trained using Multitask Learning approach. Works in literature hardly address the technical challenge of embedding such integrated DL model to be deployed on edge devices. The method provides an optimal hardware software partitioning approach for components or segments of the integrated DL model which achieves a tradeoff between latency and accuracy in object classification and localization.

Abstract: Automatic speech recognition techniques are implemented in resource constrained devices such as edge devices in internet of things where on-device speech recognition is required for low latency and privacy preservation. Existing neural network models for speech recognition have a large size and are not suitable for deployment in such devices. The present disclosure provides an architecture of a size constrained neural network and a method of training the size constrained neural network. The architecture of the size constrained neural network provides a way of increasing or decreasing number of feature blocks to achieve an accuracy-model size trade off. The method of training the size constrained neural network comprises creating a training dataset with short utterances and training the size constrained neural network with the training dataset to learn short term dependencies in the utterances. The trained size constrained neural network model is suitable for deployment in resource constrained devices.