Analyzing Evolved Fault-Tolerant Neurocontrollers

نویسنده

  • Alon Keinan
چکیده

Evolutionary autonomous agents whose behavior is determined by a neurocontroller “brain” are a promising model for studying neural processing. Nevertheless, they are missing an important quality prevalently found in all levels of natural systems, fault-tolerance, the lack of which results in overly simplistic neurocontrollers. We present a way of modifying a given evolutionary process for encouraging the creation of neurocontrollers that manifest high levels of fault-tolerance, using both direct and incremental evolutions. The evolved neurocontrollers are more robust not only against the faults introduced during the evolutionary process, but also against much more extreme ones. This robustness poses a great challenge for an analysis of the workings of the neurocontrollers, the latter being the focus of this paper: We utilize the Multi-perturbation Shapley value Analysis (MSA) to uncover the important neurons, as well as the interactions between them, revealing the mechanisms underlying the evolved faulttolerance.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

F Ur Mathematik in Den Naturwissenschaften Leipzig Balancing Rotators with Evolved Neurocontrollers Balancing Rotators with Evolved Neurocontrollers

The presented evolutionary algorithm is especially designed to generate recurrent neural networks with non-trivial internal dynamics. It is not based on genetic algorithms, and sets no constraints on the number of neu-rons and the architecture of a network. Network topology and parameters like synaptic weights and bias terms are developed simultaneously. It is well suited for generating neuromo...

متن کامل

Genetic Learning Based Fault Tolerant Cover for Digital Systems

This work proposes a genetic algorithm based technique to learn the structural description of the circuit under study, in order to give it an on line fault tolerant cover. As the circuit operates, its input / output sequences are used to learn the structural configuration of the hardware. Once the structure is evolved, the algorithm redistributes the available redundancy and generates multiple ...

متن کامل

Fault Tolerant Control of a Pmsm Drive in the Selected Emergency Conditions

The paper describes an investigation of fault tolerant control strategies for permanent magnet synchronous motor (PMSM) driven by a fault-tolerant inverter. The inverter is a topology-modified inverter with fault-tolerant capability, which can be configured as the standard 3-phase 6-switch inverter and reconfigured as 3-phase 4-switch or 2-phase 4switch inverter under the fault condition. By an...

متن کامل

Pole-Balancing with Different Evolved Neurocontrollers

The paper presents various evolved neurocontrollers for the pole-balancing problem with good benchmark performance. They are small neural networks with recurrent connectivity. The applied evolutionary algorithm, which is not based on genetic algorithms, was designed to evolve neural networks with arbitrary connectivity. It uses no quantization of inputs, outputs or internal parameters, and sets...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004