Related papers: ReDON: Recurrent Diffractive Optical Neural Proces…

A critical feature in signal processing is the ability to interpret correlations in time series signals, such as speech. Machine learning systems process this contextual information by tracking internal states in recurrent neural networks…

Photonic neural networks perform brain-inspired computations using photons instead of electrons that can achieve substantially improved computing performance. However, existing architectures can only handle data with regular structures,…

We present a novel convolutional neural network that learns to match images of an object taken from different viewpoints or by different optical sensors. Our Re-Identification Across Domain Network (RADON) scores pairs of input images from…

We introduce a deep residual recurrent neural network (DR-RNN) as an efficient model reduction technique for nonlinear dynamical systems. The developed DR-RNN is inspired by the iterative steps of line search methods in finding the residual…

Recurrent neural networks (RNNs) are well suited for solving sequence tasks in resource-constrained systems due to their expressivity and low computational requirements. However, there is still a need to bridge the gap between what RNNs are…

While differentiable logic gates have shown promise in feedforward networks, their application to sequential modeling remains unexplored. This paper presents the first implementation of Recurrent Deep Differentiable Logic Gate Networks…

Recurrent neural networks (RNNs) such as Long Short Term Memory (LSTM) networks have become popular in a variety of applications such as image processing, data classification, speech recognition, and as controllers in autonomous systems. In…

We present Linear Diffusion Networks (LDNs), a novel architecture that reinterprets sequential data processing as a unified diffusion process. Our model integrates adaptive diffusion modules with localized nonlinear updates and a…

Resistive Random Access Memory (ReRAM) based Processing In Memory (PIM) Accelerator has emerged as a promising computing architecture for memory intensive applications, such as Deep Neural Networks (DNNs). However, due to its immaturity,…

Deep neural networks (DNNs) are reshaping the field of information processing. With their exponential growth challenging existing electronic hardware, optical neural networks (ONNs) are emerging to process DNN tasks in the optical domain…

6-DoF object pose estimation from a monocular image is challenging, and a post-refinement procedure is generally needed for high-precision estimation. In this paper, we propose a framework based on a recurrent neural network (RNN) for…

In this work, we present a compact, modular framework for constructing novel recurrent neural architectures. Our basic module is a new generic unit, the Transition Based Recurrent Unit (TBRU). In addition to hidden layer activations, TBRUs…

Optical imaging and sensing systems based on diffractive elements have seen massive advances over the last several decades. Earlier generations of diffractive optical processors were, in general, designed to deliver information to an…

Circuits of biological neurons, such as in the functional parts of the brain can be modeled as networks of coupled oscillators. Inspired by the ability of these systems to express a rich set of outputs while keeping (gradients of) state…

Recurrent neural networks excel at temporal tasks and video processing but require energy-intensive sequential memory operations. We demonstrate that multimode optical fibers naturally implement spatiotemporal recurrent computation through…

Simulation and optimization are crucial for advancing the engineering design of complex systems and processes. Traditional optimization methods require substantial computational time and effort due to their reliance on resource-intensive…

As a representative next-generation device/circuit technology beyond CMOS, diffractive optical neural networks (DONNs) have shown promising advantages over conventional deep neural networks due to extreme fast computation speed (light…

Nonlinear computation is essential for various information processing tasks. Optical implementations are attractive because passive light propagation can manipulate high-dimensional signals with extreme throughput and parallelism; yet…

Optical neural networks (ONNs) are emerging as a promising neuromorphic computing paradigm for object recognition, offering unprecedented advantages in light-speed computation, ultra-low power consumption, and inherent parallelism. However,…

Medical imaging is nowadays a pillar in diagnostics and therapeutic follow-up. Current research tries to integrate established - but ionizing - tomographic techniques with technologies offering reduced radiation exposure. Diffuse Optical…