solidot新版网站常见问题,请点击这里查看。
消息
本文已被查看5567次
Artificial Neural Network Approach for Solving Fractional order initial value problems. (arXiv:1810.04992v1 [math.AP])
来源于:arXiv
In this paper, an Artificial Neural Network (ANN) technique is developed to
find solution of celebrated Fractional order Differential Equations (FDE).
Compared to integer order differential equation, FDE has the advantage that it
can better describe sometimes various real world application problems of
physical systems. Here we have employed multi-layer feed forward neural
architecture and error back propagation algorithm with unsupervised learning
for minimizing the error function and modification of the parameters (weights
and biases). Combining the initial conditions with the ANN output gives us a
suitable approximate solution of FDE. To prove the applicability of the
concept, some illustrative examples are provided to demonstrate the precision
and effectiveness of this method. Comparison of the present results with other
available results by traditional methods shows a close match which establishes
its correctness and accuracy of this method. 查看全文>>