Related papers: Optical Neural Networks: The 3D connection

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,…

Despite the success of CNNs, selecting the optimal architecture for a given task remains an open problem. Instead of aiming to select a single optimal architecture, we propose a "fabric" that embeds an exponentially large number of…

Emergent nanoscale non-volatile memory technologies with high integration density offer a promising solution to overcome the scalability limitations of CMOS-based neural networks architectures, by efficiently exhibiting the key principle of…

Accurate physical modeling with 3D-printing techniques could lead to new approaches to study structure and dynamics of biological systems complementing computational methods. Computational biology has become an important part of research…

Conventional integrated circuits (ICs) struggle to meet the escalating demands of artificial intelligence (AI). This has sparked a renewed interest in an unconventional computing paradigm: neuromorphic (brain-inspired) computing. However,…

Deep neural networks (DNN) are the state of the art on many engineering problems such as computer vision and audition. A key factor in the success of the DNN is scalability - bigger networks work better. However, the reason for this…

This paper presents an implementation of multilayer feed forward neural networks (NN) to optimize CMOS analog circuits. For modeling and design recently neural network computational modules have got acceptance as an unorthodox and useful…

Artificial neural networks (ANNs), have become ubiquitous and revolutionized many applications ranging from computer vision to medical diagnoses. However, they offer a fundamentally connectionist and distributed approach to computing, in…

The segmentation of medical images is important for the improvement and creation of healthcare systems, particularly for early disease detection and treatment planning. In recent years, the use of convolutional neural networks (CNNs) and…

Diffusion models have emerged as the best approach for generative modeling of 2D images. Part of their success is due to the possibility of training them on millions if not billions of images with a stable learning objective. However,…

Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and require long training time. To…

Optical neural networks offer a route to low-latency and energy-efficient inference by encoding computation in light propagation. However, most existing implementations rely on planar photonic circuits or discretely spaced diffractive…

Photonic neural networks (PNNs) of sufficiently large physical dimensions and high operation accuracies are envisaged as an ideal candidate for breaking the major bottlenecks in the current artificial intelligence architectures in terms of…

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…

Additive manufacturing, also known as 3D printing, is an advanced manufacturing technique that allows the fabrication of arbitrary macroscopic and microscopic objects. All 3D printing systems require large optical elements or nozzles in…

Recently, deep neural networks (DNNs) have shown advantages in accelerating optimization algorithms. One approach is to unfold finite number of iterations of conventional optimization algorithms and to learn parameters in the algorithms.…

While convolutional neural networks (CNNs) have recently made great strides in supervised classification of data structured on a grid (e.g. images composed of pixel grids), in several interesting datasets, the relations between features can…

State-of-the-art approaches for the semantic labeling of LiDAR point clouds heavily rely on the use of deep Convolutional Neural Networks (CNNs). However, transferring network architectures across different LiDAR sensor types represents a…

Object viewpoint estimation from 2D images is an essential task in computer vision. However, two issues hinder its progress: scarcity of training data with viewpoint annotations, and a lack of powerful features. Inspired by the growing…

Recent advancements in deep learning techniques have spurred considerable interest in their application to hyperspectral imagery processing. This paper provides a comprehensive review of the latest developments in this field, focusing on…