Related papers: Hardware-In-The-Loop Training of a 4f Optical Corr…

Illumination using correlated photon sources has been established as an approach to allowing high-fidelity images to be reconstructed from noisy camera frames by taking advantage of the knowledge that signal photons are spatially correlated…

Distributed learning is widely used for training large models on large datasets by distributing parts of the model or dataset across multiple devices and aggregating the computed results for subsequent computations or parameter updates.…

Large language models (LLMs) have made fundamental contributions over the last a few years. To train an LLM, one needs to alternatingly run `forward' computations and `backward' computations. The forward computation can be viewed as…

We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networks with many sorts of learners, including networks whose…

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection…

We demonstrate, for the first time, experimental over-the-fiber training of transmitter neural networks (NNs) using reinforcement learning. Optical back-to-back training of a novel NN-based digital predistorter outperforms arcsine-based…

In recent developments in the field of Computer Vision, a rise is seen in the use of transformer-based architectures. They are surpassing the state-of-the-art set by CNN architectures in accuracy but on the other hand, they are…

Mixed-signal artificial neural networks (ANNs) that employ analog matrix-multiplication accelerators can achieve higher speed and improved power efficiency. Though analog computing is known to be susceptible to noise and device…

Quantization of the weights and activations is one of the main methods to reduce the computational footprint of Deep Neural Networks (DNNs) training. Current methods enable 4-bit quantization of the forward phase. However, this constitutes…

Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and…

Domain-specialized FPGAs have delivered unprecedented performance for low-latency inference across scientific and industrial workloads, yet nearly all existing accelerators assume static models trained offline, relegating learning and…

Analog neuromorphic photonic processors are uniquely positioned to harness the ultrafast bandwidth and inherent parallelism of light, enabling scalability, on-chip integration and significant improvement in computational performance.…

Structural pruning techniques are essential for deploying multimodal large language models (MLLMs) across various hardware platforms, from edge devices to cloud servers. However, current pruning methods typically determine optimal…

The long-held assumption that backpropagation (BP) is essential for state-of-the-art performance is challenged by this work. We present rigorous, hardware-validated evidence that the Mono-Forward (MF) algorithm, a backpropagation-free…

An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner.…

We demonstrate the application of a two stage machine learning algorithm that enables to correlate the electrical signals from a GaAs$_x$N$_{1-x}$ circular polarimeter with the intensity, degree of circular polarization and handedness of an…

Low latency, high throughput inference on Convolution Neural Networks (CNNs) remains a challenge, especially for applications requiring large input or large kernel sizes. 4F optics provides a solution to accelerate CNNs by converting…

This work presents a novel Convolutional Neural Network (CNN) architecture and a training procedure to enable robust and accurate pose estimation of a noncooperative spacecraft. First, a new CNN architecture is introduced that has scored a…

Object trackers based on Convolution Neural Network (CNN) have achieved state-of-the-art performance on recent tracking benchmarks, while they suffer from slow computational speed. The high computational load arises from the extraction of…

We experimentally demonstrate classification of 4x4 binary images into 4 classes, using a 3-layer mixed-signal neuromorphic network ("MLP perceptron"), based on two passive 20x20 memristive crossbar arrays, board-integrated with discrete…