Learning Device Models with Recurrent Neural Networks

Clemens, John

doi:10.1109/ijcnn.2018.8489466

Cited by 2 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, beside DIFT-based monitoring security policies it is necessary to devise efficient and scalable verification techniques and coverage metrics that are tailored for security policies and complement existing functional verification. Another interesting direction to support DIFT would be to automatically learn the data flow relations, e.g., based on neural networks [96], within a SystemC-based peripheral to avoid a manual DIFT integration into every peripheral.…”

Section: Challenges and Future Workmentioning

confidence: 99%

Advanced virtual prototyping for cyber-physical systems using RISC-V: implementation, verification and challenges

Herdt

Drechsler

2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Virtual prototypes (VPs) are crucial in today’s design flow. VPs are predominantly created in SystemC transaction-level modeling (TLM) and are leveraged for early software development and other system-level use cases. Recently, virtual prototyping has been introduced for the emerging RISC-V instruction set architecture (ISA) and become an important piece of the growing RISC-V ecosystem. In this paper, we present enhanced virtual prototyping solutions tailored for RISC-V. The foundation is an advanced open source RISC-V VP implemented in SystemC TLM and designed as a configurable and extensible platform. It scales from small bare-metal systems to large multi-core systems that run applications on top of the Linux operating system. Based on the RISC-V VP, this paper also discusses advanced VP-based verification approaches and open challenges. In combination, we provide for the first time an integrated and unified overview and perspective on advanced virtual prototyping for RISC-V.

show abstract

Section: Challenges and Future Workmentioning

confidence: 99%

Advanced virtual prototyping for cyber-physical systems using RISC-V: implementation, verification and challenges

Herdt

Drechsler

2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…• MLDS-DS1 (41,000): RNNs Mimicking Simple Machines The MLDS datasets are available to download 5 and contain the trained networks in PyTorch format, a JSON file per example containing just the weights of the network, and a README describing the directory structure.…”

Section: Componentsmentioning

confidence: 99%

“…MLDS-DS1 contains 41,000 neural networks trained to mimic one of 5 simple machines of increasing complexity shown in Figure 3.2.1. These machines are variants of those originally introduced in [5], and consist of 8 input signals that can be driven high or low, and produce 8 output signals, based on the previous sequence of input signals. We use these simple machines as they are both easy to train and easy to modify with a backdoor as we'll see in MLDS-DS2.…”

Section: Mlds-ds1: Rnns Mimicking Simple Machinesmentioning

confidence: 99%

MLDS: A Dataset for Weight-Space Analysis of Neural Networks

Clemens

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Neural networks are powerful models that solve a variety of complex real-world problems. However, the stochastic nature of training and large number of parameters in a typical neural model makes them difficult to evaluate via inspection. Research shows this opacity can hide latent undesirable behavior, be it from poorly representative training data or via malicious intent to subvert the behavior of the network, and that this behavior is difficult to detect via traditional indirect evaluation criteria such as loss. Therefore, it is time to explore direct ways to evaluate a trained neural model via its structure and weights. In this paper we present MLDS, a new dataset consisting of thousands of trained neural networks with carefully controlled parameters and generated via a global volunteer-based distributed computing platform. This dataset enables new insights into both model-to-model and model-to-trainingdata relationships. We use this dataset to show clustering of models in weight-space with identical training data and meaningful divergence in weight-space with even a small change to the training data, suggesting that weight-space analysis is a viable and effective alternative to loss for evaluating neural networks.

show abstract

Learning Device Models with Recurrent Neural Networks

Cited by 2 publications

References 24 publications

Advanced virtual prototyping for cyber-physical systems using RISC-V: implementation, verification and challenges

Advanced virtual prototyping for cyber-physical systems using RISC-V: implementation, verification and challenges

MLDS: A Dataset for Weight-Space Analysis of Neural Networks

Contact Info

Product

Resources

About