Hybrid Convolutional Neural Networks with Reliability Guarantee

• URL: http://arxiv.org/abs/2405.05146v2
• Date: Thu, 9 May 2024 09:31:36 GMT
• Title: Hybrid Convolutional Neural Networks with Reliability Guarantee
• Authors: Hans Dermot Doran, Suzana Veljanovska,
• Abstract summary: We propose redundant execution as a well-known technique that can be used to ensure reliable execution of the AI model. This generic technique will extend the application scope of AI-accelerators that do not feature well-documented safety or dependability properties.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Making AI safe and dependable requires the generation of dependable models and dependable execution of those models. We propose redundant execution as a well-known technique that can be used to ensure reliable execution of the AI model. This generic technique will extend the application scope of AI-accelerators that do not feature well-documented safety or dependability properties. Typical redundancy techniques incur at least double or triple the computational expense of the original. We adopt a co-design approach, integrating reliable model execution with non-reliable execution, focusing that additional computational expense only where it is strictly necessary. We describe the design, implementation and some preliminary results of a hybrid CNN.

Related papers

• Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models [21.88436406884943]
  We introduce EED, which diversifies the compression of a single base model based on different pruning importance scores and enhances ensemble diversity to achieve high adversarial robustness and resource efficiency. EED demonstrated state-of-the-art performance compared to existing adversarial pruning techniques, along with an inference speed improvement of up to 1.86 times.
  arXiv  Detail & Related papers  (2025-04-07T05:41:35Z)
• Workflow for Safe-AI [0.0]
  Development and deployment of safe and dependable AI models is crucial in applications where functional safety is a key concern. This work proposes a transparent, complete, yet flexible and lightweight workflow that highlights both reliability and qualifiability.
  arXiv  Detail & Related papers  (2025-03-18T07:45:18Z)
• Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models [93.76814568163353]
  We propose a novel bilevel optimization framework for pruned diffusion models. This framework consolidates the fine-tuning and unlearning processes into a unified phase. It is compatible with various pruning and concept unlearning methods.
  arXiv  Detail & Related papers  (2024-12-19T19:13:18Z)
• Automatically Learning Hybrid Digital Twins of Dynamical Systems [56.69628749813084]
  Digital Twins (DTs) simulate the states and temporal dynamics of real-world systems. DTs often struggle to generalize to unseen conditions in data-scarce settings. In this paper, we propose an evolutionary algorithm ($textbfHDTwinGen$) to autonomously propose, evaluate, and optimize HDTwins.
  arXiv  Detail & Related papers  (2024-10-31T07:28:22Z)
• Generative Diffusion-based Contract Design for Efficient AI Twins Migration in Vehicular Embodied AI Networks [55.15079732226397]
  Embodied AI is a rapidly advancing field that bridges the gap between cyberspace and physical space. In VEANET, embodied AI twins act as in-vehicle AI assistants to perform diverse tasks supporting autonomous driving.
  arXiv  Detail & Related papers  (2024-10-02T02:20:42Z)
• Exploring Cross-model Neuronal Correlations in the Context of Predicting Model Performance and Generalizability [2.6708879445664584]
  This paper introduces a novel approach for assessing a newly trained model's performance based on another known model. The proposed method evaluates correlations by determining if, for each neuron in one network, there exists a neuron in the other network that produces similar output.
  arXiv  Detail & Related papers  (2024-08-15T22:57:39Z)
• Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inference [11.39873199479642]
  Nesa introduces a model-agnostic sharding framework designed for decentralized AI inference. Our framework uses blockchain-based deep neural network sharding to distribute computational tasks across a diverse network of nodes. Our results highlight the potential to democratize access to cutting-edge AI technologies.
  arXiv  Detail & Related papers  (2024-07-29T08:18:48Z)
• Multifidelity Cross-validation [0.0]
  We are interested in emulating quantities of interest observed from models of a system at multiple fidelities. We propose a novel method to actively learn the surrogate model via leave-one-out cross-validation (LOO-CV) We demonstrate the utility of our method on several synthetic test problems as well as on the thermal stress analysis of a gas turbine blade.
  arXiv  Detail & Related papers  (2024-07-01T17:42:11Z)
• Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models [54.132297393662654]
  We introduce a hybrid method that fine-tunes cutting-edge diffusion models by optimizing reward models through RL. We demonstrate the capability of our approach to outperform the best designs in offline data, leveraging the extrapolation capabilities of reward models.
  arXiv  Detail & Related papers  (2024-05-30T03:57:29Z)
• One-Shot Safety Alignment for Large Language Models via Optimal Dualization [64.52223677468861]
  This paper presents a perspective of dualization that reduces constrained alignment to an equivalent unconstrained alignment problem. We do so by pre-optimizing a smooth and convex dual function that has a closed form. Our strategy leads to two practical algorithms in model-based and preference-based settings.
  arXiv  Detail & Related papers  (2024-05-29T22:12:52Z)
• Input Convex Lipschitz RNN: A Fast and Robust Approach for Engineering Tasks [14.835081385422653]
  We develop a novel network architecture, termed Input Convex Lipschitz Recurrent Neural Networks. This model is explicitly designed for fast and robust optimization-based tasks. We have successfully implemented this model in various practical engineering applications.
  arXiv  Detail & Related papers  (2024-01-15T06:26:53Z)
• Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows [54.050498411883495]
  We develop a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows. We show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the textitPR-divergences. Our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.
  arXiv  Detail & Related papers  (2023-05-30T10:07:17Z)
• GAR: Generalized Autoregression for Multi-Fidelity Fusion [16.464126364802283]
  Generalized autoregression (GAR) is proposed to combine the results of low-fidelity (fast but inaccurate) and high-fidelity (slow but accurate) simulations. Gar can deal with arbitrary dimensional outputs and arbitrary multifidelity data structure to satisfy the demand of multi-fidelity fusion. Gar consistently outperforms the SOTA methods with a large margin (up to 6x improvement in RMSE) with only a couple high-fidelity training samples.
  arXiv  Detail & Related papers  (2023-01-13T19:10:25Z)
• An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices [58.62801151916888]
  We introduce a new sparsity dimension, namely pattern-based sparsity that comprises pattern and connectivity sparsity, and becoming both highly accurate and hardware friendly. Our approach on the new pattern-based sparsity naturally fits into compiler optimization for highly efficient DNN execution on mobile platforms.
  arXiv  Detail & Related papers  (2020-01-20T16:17:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.