Logic Circuit Based Test Derivation for Microcontrollers

Laputenko, Andrey

doi:10.1109/edm.2019.8823364

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the importance of developing an efficient state machine for multitask cooperation, this has been neglected for a long time and its development is stalled. Instead, most of the recent efforts are directed on applying the traditional state machine in some specific domains, such as deriving tests [19,20], automatically generating Ethereum contracts [21], scalable state machine replication [22] and road network extraction [23]. In addition, these studies only deal with one kind of neural networks, which limits their application scenarios.…”

Section: Introductionmentioning

confidence: 99%

Hybrid neural state machine for neural network

Tian

Wu²,

2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

The integration of computer-science-oriented and neuroscience-oriented approaches is believed to be a promising way for the development of artificial general intelligence (AGI). Recently, a hybrid Tianjic chip that integrates both approaches has been reported, providing a general platform to facilitate the research of AGI. The control algorithm for handling various neural networks is the key to this platform; however, it is still primitive. In this work, we propose a hybrid neural state machine (H-NSM) framework that can efficiently cooperate with artificial neural networks and spiking neural networks and control the workflows to accomplish complex tasks. The H-NSM receives input from different types of networks, makes decisions according to the fusing of various information, and sends control signals to the sub-network or actuator. The H-NSM can be trained to adapt to context-aware tasks or sequential tasks, thereby improving system robustness. The training algorithm works correctly even if only 50% of the forced state information is provided. It achieved performance comparable to the optimum algorithm on the Tower of Hanoi task and achieved multiple tasks control on a self-driving bicycle. After only 50 training epochs, the transfer accuracy reaches 100% in the test case. It proves that H-NSM has the potential to advance control logic for hybrid systems, paving the way for designing complex intelligent systems and facilitating the research towards AGI.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid neural state machine for neural network

Tian

Wu²,

2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The general acceptance of the finite state machine as a canonical model of finite-state computation can be attributed to the robustness of the model and the appeal of theory . It has been widely used in various application scenarios, such as colored Petri nets, deriving tests, , automatically generating Ethereum contracts, scalable state machine replication, and road network extraction . Recently, there has been increasing interest in applying the traditional neural networks to design state machines to realize state control. − This kind of neural state machine (NSM) is proven to be feasible and effective.…”

Section: Introductionmentioning

confidence: 99%

High Robustness Memristor Neural State Machines

Tian

Wang

Shi

et al. 2020

ACS Appl. Electron. Mater.

View full text Add to dashboard Cite

Neural state machines (NSMs) with weight tunable synapses and leaky integrate-and-fire neurons can control the workflow according to the input information and current state, which has attracted increasing attention in handling complex control logic for various applications. The emerging memristor crossbar network provides an opportunity to further develop NSMs due to the unique analog properties, high density, low-power consumption, and high scalability. However, memristors exhibit nonideal features, such as variation, nonlinearity, and asymmetry of the conductance update, which may hinder the implementation of memristors in NSMs. In this paper, we investigate the implementation of a memristor in an NSM and demonstrate a fully memristor neural state machine (MNSM). Nonvolatile and volatile memristors are designed to emulate the synaptic and neuronal behaviors in MNSMs, respectively. Through a map search task, the MNSM not only exhibits strong robustness to the substantial nonideal behaviors of memristors but also benefits from these shortcomings, showing a faster convergence in the training process. This work proves the feasibility of applying memristors in NSMs and the great potential of MNSMs in handling complex control logic, which promotes the further development of NSMs for neuromorphic computing systems.

show abstract

Logic Circuit Based Test Derivation for Microcontrollers

Cited by 2 publications

References 6 publications

Hybrid neural state machine for neural network

Hybrid neural state machine for neural network

High Robustness Memristor Neural State Machines

Contact Info

Product

Resources

About