Condensing CNNs with Partial Differential Equations

Kag, Anil; Saligrama, Venkatesh

doi:10.1109/cvpr52688.2022.00069

Cited by 4 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kairos [57], on the other hand, leverages a query distribution to optimially utilize heterogenous cloud resources. Finally, hybrid models [58] smartly balances the accuracy guaranteed by inference performed on large models, which can be deployed in the cloud, with the low latency achieved through running smaller models in edge environments. By automatically filtering particularly demanding queries and sending them to the cloud, the system successfully integrates two sides of the Cloud-Edge-IoT continuum.…”

Section: Machine Learning Inference Systemsmentioning

confidence: 99%

Flexible Deployment of Machine Learning Inference Pipelines in the Cloud–Edge–IoT Continuum

Bogacka,

Sowiński,

Danilenka

et al. 2024

Electronics

View full text Add to dashboard Cite

Currently, deploying machine learning workloads in the Cloud–Edge–IoT continuum is challenging due to the wide variety of available hardware platforms, stringent performance requirements, and the heterogeneity of the workloads themselves. To alleviate this, a novel, flexible approach for machine learning inference is introduced, which is suitable for deployment in diverse environments—including edge devices. The proposed solution has a modular design and is compatible with a wide range of user-defined machine learning pipelines. To improve energy efficiency and scalability, a high-performance communication protocol for inference is propounded, along with a scale-out mechanism based on a load balancer. The inference service plugs into the ASSIST-IoT reference architecture, thus taking advantage of its other components. The solution was evaluated in two scenarios closely emulating real-life use cases, with demanding workloads and requirements constituting several different deployment scenarios. The results from the evaluation show that the proposed software meets the high throughput and low latency of inference requirements of the use cases while effectively adapting to the available hardware. The code and documentation, in addition to the data used in the evaluation, were open-sourced to foster adoption of the solution.

show abstract

Section: Machine Learning Inference Systemsmentioning

confidence: 99%

Flexible Deployment of Machine Learning Inference Pipelines in the Cloud–Edge–IoT Continuum

Bogacka,

Sowiński,

Danilenka

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Additionally, it leverages the strengths of sequential networks such as Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks in modeling temporal dependencies, crucial for tasks involving time series data like language modeling or remaining useful life (RUL) prediction. Notably, the TCN model successfully addresses the issue of gradient explosion inherent in RNNs and LSTMs [23], [24], ensuring stable and convergent training.This enhances the model's trainability and generalization performance.…”

Section: Introductionmentioning

confidence: 99%

Temporal Convolutional Network with Attention Mechanism for Bearing Remaining Useful Life Prediction

Wang

Zhang

et al. 2023

Mechanisms and Machine Science

View full text Add to dashboard Cite

Accurate prediction of the Remaining Useful Life (RUL) of rolling bearings is crucial in industrial production, yet existing models often struggle with limited generalization capabilities due to their inability to fully process all vibration signal patterns. We introduce a novel multi-input autoregressive model to address this challenge in RUL prediction for bearings. Our approach uniquely integrates vibration signals with previously predicted Health Indicator (HI) values, employing feature fusion to output current window HI values. Through autoregressive iterations, the model attains a global receptive field, effectively overcoming the limitations in generalization. Furthermore, we innovatively incorporate a segmentation method and multiple training iterations to mitigate error accumulation in autoregressive models. Empirical evaluation on the PMH2012 dataset demonstrates that our model, compared to other backbone networks using similar autoregressive approaches, achieves significantly lower Root Mean Square Error (RMSE) and Score. Notably, it outperforms traditional autoregressive models that use label values as inputs and non-autoregressive networks, showing superior generalization abilities with a marked lead in RMSE and Score metrics.

show abstract

Enhancing Anomaly Detection in Noisy Images: Unleashing the Power of Attention-Aware PDE Constraint Feature Denoiser Module

Jha,

Siva Sai Teja,

Wadawadagi

et al. 2024

2024 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Condensing CNNs with Partial Differential Equations

Cited by 4 publications

References 7 publications

Flexible Deployment of Machine Learning Inference Pipelines in the Cloud–Edge–IoT Continuum

Flexible Deployment of Machine Learning Inference Pipelines in the Cloud–Edge–IoT Continuum

Temporal Convolutional Network with Attention Mechanism for Bearing Remaining Useful Life Prediction

Enhancing Anomaly Detection in Noisy Images: Unleashing the Power of Attention-Aware PDE Constraint Feature Denoiser Module

Contact Info

Product

Resources

About