Genetically programmable optical random neural networks
- URL: http://arxiv.org/abs/2403.12490v2
- Date: Thu, 13 Feb 2025 18:59:23 GMT
- Title: Genetically programmable optical random neural networks
- Authors: Bora Çarpınlıoğlu, Uğur Teğin,
- Abstract summary: We demonstrate a genetically programmable yet simple optical neural network to achieve high performances with optical random projection.
Our novel technique finds an optimum kernel and improves initial test accuracies by 8-41% for various machine learning tasks.
- Score: 0.0
- License:
- Abstract: Today, machine learning tools, particularly artificial neural networks, have become crucial for diverse applications. However, current digital computing tools to train and deploy artificial neural networks often struggle with massive data sizes and high power consumptions. Optical computing provides inherent parallelism accommodating high-resolution input data and performs fundamental operations with passive optical components. However, most of the optical computing platforms suffer from relatively low accuracies for machine learning tasks due to fixed connections while avoiding complex and sensitive techniques. Here, we demonstrate a genetically programmable yet simple optical neural network to achieve high performances with optical random projection. By genetically programming the orientation of the scattering medium which acts as a random projection kernel and only using 1% of the search space, our novel technique finds an optimum kernel and improves initial test accuracies by 8-41% for various machine learning tasks. Through numerical simulations and experiments on a number of datasets, we validate the programmability and high-resolution sample processing capabilities of our design. Our optical computing method presents a promising approach to achieve high performance in optical neural networks with a simple and scalable design.
Related papers
- Training Hybrid Neural Networks with Multimode Optical Nonlinearities Using Digital Twins [2.8479179029634984]
We introduce ultrashort pulse propagation in multimode fibers, which perform large-scale nonlinear transformations.
Training the hybrid architecture is achieved through a neural model that differentiably approximates the optical system.
Our experimental results achieve state-of-the-art image classification accuracies and simulation fidelity.
arXiv Detail & Related papers (2025-01-14T10:35:18Z) - Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
Task-oriented edge computing addresses this by shifting data analysis to the edge.
Existing methods struggle to balance high model performance with low resource consumption.
We propose a novel co-design framework to optimize neural network architecture.
arXiv Detail & Related papers (2024-10-29T19:02:54Z) - Optical training of large-scale Transformers and deep neural networks with direct feedback alignment [48.90869997343841]
We experimentally implement a versatile and scalable training algorithm, called direct feedback alignment, on a hybrid electronic-photonic platform.
An optical processing unit performs large-scale random matrix multiplications, which is the central operation of this algorithm, at speeds up to 1500 TeraOps.
We study the compute scaling of our hybrid optical approach, and demonstrate a potential advantage for ultra-deep and wide neural networks.
arXiv Detail & Related papers (2024-09-01T12:48:47Z) - Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences.
It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations.
Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
arXiv Detail & Related papers (2024-02-20T15:23:24Z) - Training neural networks with end-to-end optical backpropagation [1.1602089225841632]
We show how to implement backpropagation, an algorithm for training a neural network, using optical processes.
Our approach is adaptable to various analog platforms, materials, and network structures.
It demonstrates the possibility of constructing neural networks entirely reliant on analog optical processes for both training and inference tasks.
arXiv Detail & Related papers (2023-08-09T21:11:26Z) - Photonics for artificial intelligence and neuromorphic computing [52.77024349608834]
Photonic integrated circuits have enabled ultrafast artificial neural networks.
Photonic neuromorphic systems offer sub-nanosecond latencies.
These systems could address the growing demand for machine learning and artificial intelligence.
arXiv Detail & Related papers (2020-10-30T21:41:44Z) - Rapid characterisation of linear-optical networks via PhaseLift [51.03305009278831]
Integrated photonics offers great phase-stability and can rely on the large scale manufacturability provided by the semiconductor industry.
New devices, based on such optical circuits, hold the promise of faster and energy-efficient computations in machine learning applications.
We present a novel technique to reconstruct the transfer matrix of linear optical networks.
arXiv Detail & Related papers (2020-10-01T16:04:22Z) - Large-scale neuromorphic optoelectronic computing with a reconfigurable
diffractive processing unit [38.898230519968116]
We propose an optoelectronic reconfigurable computing paradigm by constructing a diffractive processing unit.
It can efficiently support different neural networks and achieve a high model complexity with millions of neurons.
Our prototype system built with off-the-shelf optoelectronic components surpasses the performance of state-of-the-art graphics processing units.
arXiv Detail & Related papers (2020-08-26T16:34:58Z) - Light-in-the-loop: using a photonics co-processor for scalable training
of neural networks [21.153688679957337]
We present the first optical co-processor able to accelerate the training phase of digitally-implemented neural networks.
We demonstrate its use to train a neural network for handwritten digits recognition.
arXiv Detail & Related papers (2020-06-02T09:19:45Z) - Spiking Neural Networks Hardware Implementations and Challenges: a
Survey [53.429871539789445]
Spiking Neural Networks are cognitive algorithms mimicking neuron and synapse operational principles.
We present the state of the art of hardware implementations of spiking neural networks.
We discuss the strategies employed to leverage the characteristics of these event-driven algorithms at the hardware level.
arXiv Detail & Related papers (2020-05-04T13:24:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.