اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدMonadic Pavlovian associative learning in a backpropagation-free photonic network
262
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
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, however, it is rare to find the use of Pavlovian type associative learning for artificial intelligence (AI) applications. Instead, other biologically-inspired learning concepts, in particular artificial neural networks (ANNs) have flourished, yielding extensive impact on a wide range of fields including finance, healthcare and transportation. However, learning in such conventional ANNs, in particular in the form of modern deep neural networks (DNNs) are usually carried out using the backpropagation method, is computationally and energy intensive. Here we report the experimental demonstration of backpropagation-free learning, achieved using a single (or monadic) associative hardware element. This is realized on an integrated photonic platform using phase change materials combined with on-chip cascaded directional couplers. We link associative learning with supervised learning, based on their common goal of associating certain inputs with correct outputs. We then expand the concept to develop larger-scale supervised learning networks using our monadic Pavlovian photonic hardware, developing a distinct machine-learning framework based on single-element associations and, importantly, using backpropagation-free single-layer weight architectures to approach general learning tasks. Our approach not only significantly reduces the computational burden imposed by learning in conventional neural network approaches, thereby increasing speed and decreasing energy use during learning, but also offers higher bandwidth inherent to a photonic implementation, paving the way for future deployment of fast photonic artificially intelligent machines.
قيم البحث
اقرأ أيضاً
Recently, integrated optics has gained interest as a hardware platform for implementing machine learning algorithms. Of particular interest are artificial neural networks, since matrix-vector multi- plications, which are used heavily in artificial ne
ural networks, can be done efficiently in photonic circuits. The training of an artificial neural network is a crucial step in its application. However, currently on the integrated photonics platform there is no efficient protocol for the training of these networks. In this work, we introduce a method that enables highly efficient, in situ training of a photonic neural network. We use adjoint variable methods to derive the photonic analogue of the backpropagation algorithm, which is the standard method for computing gradients of conventional neural networks. We further show how these gradients may be obtained exactly by performing intensity measurements within the device. As an application, we demonstrate the training of a numerically simulated photonic artificial neural network. Beyond the training of photonic machine learning implementations, our method may also be of broad interest to experimental sensitivity analysis of photonic systems and the optimization of reconfigurable optics platforms.
Despite recent progress in memory augmented neural network (MANN) research, associative memory networks with a single external memory still show limited performance on complex relational reasoning tasks. Especially the content-based addressable memor
y networks often fail to encode input data into rich enough representation for relational reasoning and this limits the relation modeling performance of MANN for long temporal sequence data. To address these problems, here we introduce a novel Distributed Associative Memory architecture (DAM) with Memory Refreshing Loss (MRL) which enhances the relation reasoning performance of MANN. Inspired by how the human brain works, our framework encodes data with distributed representation across multiple memory blocks and repeatedly refreshes the contents for enhanced memorization similar to the rehearsal process of the brain. For this procedure, we replace a single external memory with a set of multiple smaller associative memory blocks and update these sub-memory blocks simultaneously and independently for the distributed representation of input data. Moreover, we propose MRL which assists a tasks target objective while learning relational information existing in data. MRL enables MANN to reinforce an association between input data and task objective by reproducing stochastically sampled input data from stored memory contents. With this procedure, MANN further enriches the stored representations with relational information. In experiments, we apply our approaches to Differential Neural Computer (DNC), which is one of the representative content-based addressing memory models and achieves the state-of-the-art performance on both memorization and relational reasoning tasks.
Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. To this end, we augment the LSTM model with an
associative memory, dubbed Fast Weight Memory (FWM). Through differentiable operations at every step of a given input sequence, the LSTM updates and maintains compositional associations stored in the rapidly changing FWM weights. Our model is trained end-to-end by gradient descent and yields excellent performance on compositional language reasoning problems, meta-reinforcement-learning for POMDPs, and small-scale word-level language modelling.
All-optical binary convolution with a photonic spiking vertical-cavity surface-emitting laser (VCSEL) neuron is proposed and demonstrated experimentally for the first time. Optical inputs, extracted from digital images and temporally encoded using re
ctangular pulses, are injected in the VCSEL neuron which delivers the convolution result in the number of fast (<100 ps long) spikes fired. Experimental and numerical results show that binary convolution is achieved successfully with a single spiking VCSEL neuron and that all-optical binary convolution can be used to calculate image gradient magnitudes to detect edge features and separate vertical and horizontal components in source images. We also show that this all-optical spiking binary convolution system is robust to noise and can operate with high-resolution images. Additionally, the proposed system offers important advantages such as ultrafast speed, high energy efficiency and simple hardware implementation, highlighting the potentials of spiking photonic VCSEL neurons for high-speed neuromorphic image processing systems and future photonic spiking convolutional neural networks.
Soliton microcombs constitute chip-scale optical frequency combs, and have the potential to impact a myriad of applications from frequency synthesis and telecommunications to astronomy. The requirement on external driving lasers has been significantl
y relaxed with the demonstration of soliton formation via self-injection locking of the pump laser to the microresonator. Yet to date, the dynamics of this process has not been fully understood. Prior models of self-injection locking were not able to explain sufficiently large detunings, crucial for soliton formation. Here we develop a theoretical model of self-injection locking to a nonlinear microresonator (nonlinear self-injection locking) for the first time and show that self- and cross-phase modulation of the clockwise and counter-clockwise light enables soliton formation. Using an integrated soliton microcomb of directly detectable 30 GHz repetition rate, consisting of a DFB laser self-injection-locked to a Si3N4 microresonator chip, we study the soliton formation dynamics via self-injection locking, as well as the repetition rate evolution, experimentally. We reveal that Kerr nonlinearity in microresonator significantly modifies locking dynamics, making laser emission frequency red detuned. We propose and implement a novel technique for measurements of the nonlinear frequency tuning curve and concurrent observation of microcomb states switching in real time.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
