Using DNNs and Smart Sampling for Coverage Closure Acceleration

Gal, Raviv; Haber, Eldad; Ziv, Avi

doi:10.1145/3380446.3430627

Cited by 7 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simulation is expensive in terms of computation and simulation time, and selecting tests that exercise the hardest-to-reach coverage tasks might require at least tens of thousands of simulation cycles to collect adequate data to learn from. As observed in [11], learning from coverage feedback in such circumstances leads to resource inefficiencies linked to obtaining the required data.…”

Section: Constraints Verification Engineermentioning

confidence: 99%

Hybrid Intelligent Testing in Simulation-Based Verification

Masamba,

Eder,

Blackmore

2022

Preprint

View full text Add to dashboard Cite

Efficient and effective testing for simulation-based hardware verification is challenging. Using constrained random test generation, several millions of tests may be required to achieve coverage goals. The vast majority of tests do not contribute to coverage progress, yet they consume verification resources. In this paper, we propose a hybrid intelligent testing approach combining two methods that have previously been treated separately, namely Coverage-Directed Test Selection and Novelty-Driven Verification. Coverage-Directed Test Selection learns from coverage feedback to bias testing towards the most effective tests. Novelty-Driven Verification learns to identify and simulate stimuli that differ from previous stimuli, thereby reducing the number of simulations and increasing testing efficiency. We discuss the strengths and limitations of each method, and we show how our approach addresses each method's limitations, leading to hardware testing that is both efficient and effective.

show abstract

Section: Constraints Verification Engineermentioning

confidence: 99%

Hybrid Intelligent Testing in Simulation-Based Verification

Masamba,

Eder,

Blackmore

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Such an approximation is sometimes referred to as a Physics-Informed Neural Network (PINN) or surrogate model (see [ 15 ] and references within). Using PINNs as surrogate models is an inexpensive approximation that replaces complex simulations and is now commonly carried out in many fields (see, e.g., [ 17 , 18 , 19 , 20 ]), ranging from flow to chemical engineering and hardware testing. We, therefore, find it appropriate to extend this methodology to protein design.…”

Section: Introductionmentioning

confidence: 99%

Protein Design Using Physics Informed Neural Networks

Omar¹,

Keasar

Ben-Sasson

et al. 2023

Biomolecules

Self Cite

View full text Add to dashboard Cite

The inverse protein folding problem, also known as protein sequence design, seeks to predict an amino acid sequence that folds into a specific structure and performs a specific function. Recent advancements in machine learning techniques have been successful in generating functional sequences, outperforming previous energy function-based methods. However, these machine learning methods are limited in their interoperability and robustness, especially when designing proteins that must function under non-ambient conditions, such as high temperature, extreme pH, or in various ionic solvents. To address this issue, we propose a new Physics-Informed Neural Networks (PINNs)-based protein sequence design approach. Our approach combines all-atom molecular dynamics simulations, a PINNs MD surrogate model, and a relaxation of binary programming to solve the protein design task while optimizing both energy and the structural stability of proteins. We demonstrate the effectiveness of our design framework in designing proteins that can function under non-ambient conditions.

show abstract

Machine Learning in the Service of Hardware Functional Verification

Gal

Ziv

2022

Machine Learning Applications in Electronic Design Automation

View full text Add to dashboard Cite

Using DNNs and Smart Sampling for Coverage Closure Acceleration

Cited by 7 publications

References 11 publications

Hybrid Intelligent Testing in Simulation-Based Verification

Hybrid Intelligent Testing in Simulation-Based Verification

Protein Design Using Physics Informed Neural Networks

Machine Learning in the Service of Hardware Functional Verification

Contact Info

Product

Resources

About