连续神经动力学的离散符号优化和玻尔兹曼采样:梯度符号计算
Discrete symbolic optimization and Boltzmann sampling by continuous neural dynamics: Gradient Symbolic Computation
摘要:
梯度符号计算被提出作为一种使用神经似然连续随机动力系统求解离散全局优化问题的手段。梯度符号动力学涉及两个自由参数,它们必须作为时间的函数进行调整,以在计算结束时获得全局最大值。我们提供了一个总结,什么是已知的GSC动态的参数设置的特殊情况下,也建立有一个时间表的两个参数,收敛到正确的答案发生的概率很高。这些结果把GSC已经获得的经验结果放在一个坚实的理论基础上。
英文摘要:
Gradient Symbolic Computation is proposed as a means of solving discrete global optimization problems using a neurally plausible continuous stochastic dynamical system. Gradient symbolic dynamics involves two free parameters that must be adjusted as a function of time to obtain the global maximizer at the end of the computation. We provide a summary of what is known about the GSC dynamics for special cases of settings of the parameters, and also establish that there is a schedule for the two parameters for which convergence to the correct answer occurs with high probability. These results put the empirical results already obtained for GSC on a sound theoretical footing.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。