Marabou 2.0: a versatile formal analyzer of neural networks

H Wu, O Isac, A Zeljić, T Tagomori, M Daggitt… - … on Computer Aided …, 2024 - Springer
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks | SpringerLink Skip to main
content Advertisement SpringerLink Account Menu Find a journal Publish with us Track your …

Robust iterative value conversion: Deep reinforcement learning for neurochip-driven edge robots

Y Kadokawa, T Kodera, Y Tsurumine… - Robotics and …, 2024 - Elsevier
A neurochip is a device that reproduces the signal processing mechanisms of brain neurons
and calculates Spiking Neural Networks (SNNs) with low power consumption and at high …

Deep Combination of CDCL (T) and Local Search for Satisfiability Modulo Non-Linear Integer Arithmetic Theory

X Zhang, B Li, S Cai - Proceedings of the IEEE/ACM 46th International …, 2024 - dl.acm.org
Satisfiability Modulo Theory (SMT) generalizes the propositional satisfiability problem (SAT)
by extending support for various first-order background theories. In this paper, we focus on …

Certified quantization strategy synthesis for neural networks

Y Zhang, G Chen, F Song, J Sun, JS Dong - International Symposium on …, 2024 - Springer
Quantization plays an important role in deploying neural networks on embedded, real-time
systems with limited computing and storage resources (eg, edge devices). It significantly …

Quantization-Based Optimization Algorithm for Hardware Implementation of Convolution Neural Networks

BJ Mohd, KM Ahmad Yousef, A AlMajali, T Hayajneh - Electronics, 2024 - mdpi.com
Convolutional neural networks (CNNs) have demonstrated remarkable performance in
many areas but require significant computation and storage resources. Quantization is an …

Automated Program Refinement: Guide and Verify Code Large Language Model with Refinement Calculus

Y Cai, Z Hou, D Sanan, X Luan, Y Lin, J Sun… - Proceedings of the …, 2025 - dl.acm.org
Recently, the rise of code-centric Large Language Models (LLMs) has reshaped the
software engineering world with low-barrier tools like Copilot that can easily generate code …

Live on the Hump: Self Knowledge Distillation via Virtual Teacher-Students Mutual Learning

S Wang, P Hao, F Wu, C Bai - … of the 32nd ACM International Conference …, 2024 - dl.acm.org
For solving the limitations of the current self knowledge distillation including never fully
utilizing the knowledge of shallow exits and neglecting the impact of auxiliary exits' structure …

Neural Network Verification is a Programming Language Challenge

LC Cordeiro, ML Daggitt, J Girard-Satabin… - ar** field of research. So far, the
main priority has been establishing efficient verification algorithms and tools, while proper …

Parallel Verification for -Equivalence of Neural Network Quantization

P Huang, Y Yang, H Wu, I Daukantas, M Wu… - … Symposium on AI …, 2024 - Springer
Quantization replaces floating point arithmetic with integer arithmetic in deep neural
networks, enabling more efficient on-device inference with less power and memory …

[PDF][PDF] Quantization-Based Optimization Algorithm for Hardware Implementation of Convolution Neural Networks. Electronics 2024, 13, 1727

BJ Mohd, KM Ahmad Yousef, A AlMajali, T Hayajneh - 2024 - researchgate.net
Convolutional neural networks (CNNs) have demonstrated remarkable performance in
many areas but require significant computation and storage resources. Quantization is an …