Neuromorphic Hardware Learns to Learn
Neuromorphic Hardware Learns to Learn
复制标题
DOI：
10.3389/fnins.2019.00483
复制
发表时间：
2019-05-21
影响因子：
4.3
通讯作者：
Maass, Wolfgang
中科院分区：
文献类型：
--
作者：
Bohnstingl, Thomas;Scherr, Franz;Maass, Wolfgang
神经形态硬件的超参数和学习算法通常是手工选择的，以适应特定的任务。相比之下，大脑中的神经元网络通过广泛的进化和发展过程进行了优化，以便在一系列计算和学习任务中发挥作用。有时，这个过程已经通过遗传算法进行了模拟，但这些算法需要自己手工设计其细节，并且往往提供有限的改进范围。相反，我们使用其他强大的无梯度优化工具，例如交叉熵方法和进化策略，以便将生物优化过程的功能移植到神经形态硬件。作为一个例子，我们展示了这些优化算法使神经形态代理能够非常有效地从奖励中学习。特别是，亚塑性，即，它们使用的学习规则的优化实质上增强了硬件的基于奖励的学习能力。此外，我们第一次展示了从这种硬件中学习的好处，特别是从以前的学习经验中提取抽象知识的能力，这加快了新的但相关的任务的学习。学习到学习特别适合于加速的神经形态硬件，因为它使执行所需的非常大量的网络计算成为可能。
Hyperparameters and learning algorithms for neuromorphic hardware are usually chosen by hand to suit a particular task. In contrast, networks of neurons in the brain were optimized through extensive evolutionary and developmental processes to work well on a range of computing and learning tasks. Occasionally this process has been emulated through genetic algorithms, but these require themselves hand-design of their details and tend to provide a limited range of improvements. We employ instead other powerful gradient-free optimization tools, such as cross-entropy methods and evolutionary strategies, in order to port the function of biological optimization processes to neuromorphic hardware. As an example, we show these optimization algorithms enable neuromorphic agents to learn very efficiently from rewards. In particular, meta-plasticity, i.e., the optimization of the learning rule which they use, substantially enhances reward-based learning capability of the hardware. In addition, we demonstrate for the first time Learning-to-Learn benefits from such hardware, in particular, the capability to extract abstract knowledge from prior learning experiences that speeds up the learning of new but related tasks. Learning-to-Learn is especially suited for accelerated neuromorphic hardware, since it makes it feasible to carry out the required very large number of network computations.