当前位置: X-MOL 学术Optica › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Monadic Pavlovian associative learning in a backpropagation-free photonic network
Optica ( IF 10.4 ) Pub Date : 2022-07-14 , DOI: 10.1364/optica.455864
James You Sian Tan , Zengguang Cheng , Johannes Feldmann , Xuan Li , Nathan Youngblood , Utku Emre Ali , David Wright , Wolfram Pernice , Harish Bhaskaran

Over a century ago, Ivan P. Pavlov, in a classic experiment, demonstrated how dogs can learn to associate a ringing bell with food, thereby causing a ring to result in salivation. Today, it is rare to find the use of Pavlovian type associative learning for artificial intelligence applications even though other learning concepts, in particular, backpropagation on artificial neural networks (ANNs), have flourished. However, training using the backpropagation method on “conventional” ANNs, especially in the form of modern deep neural networks, is computationally and energy intensive. Here, we experimentally demonstrate a form of backpropagation-free learning using a single (or monadic) associative hardware element. We realize this on an integrated photonic platform using phase-change materials combined with on-chip cascaded directional couplers. We then develop a scaled-up circuit network using our monadic Pavlovian photonic hardware that delivers a distinct machine learning framework based on single-element associations and, importantly, using backpropagation-free architectures to address general learning tasks. Our approach reduces the computational burden imposed by learning in conventional neural network approaches, thereby increasing speed while also offering a higher bandwidth inherent to our photonic implementation.

中文翻译:

无反向传播光子网络中的一元巴甫洛夫联想学习

一个多世纪前,Ivan P. Pavlov 在一项经典实验中展示了狗如何学会将铃声与食物联系起来,从而使铃声产生流涎。今天,尽管其他学习概念,特别是人工神经网络 (ANN) 上的反向传播已经蓬勃发展,但很少发现将巴甫洛夫式联想学习用于人工智能应用。然而,在“传统”人工神经网络上使用反向传播方法进行训练,尤其是现代深度神经网络的形式,在计算上和能量上都是密集型的。在这里,我们通过实验证明了一种使用单个(或单子)关联硬件元素的无反向传播学习形式。我们在集成光子平台上实现了这一点,该平台使用相变材料与片上级联定向耦合器相结合。然后,我们使用我们的一元巴甫洛夫光子硬件开发了一个放大的电路网络,该硬件提供了一个基于单元素关联的独特机器学习框架,重要的是,使用无反向传播架构来解决一般学习任务。我们的方法减少了传统神经网络方法中学习所带来的计算负担,从而提高了速度,同时还为我们的光子实现提供了更高的带宽。
更新日期:2022-07-14
down
wechat
bug