Related papers: Neuro-inspired automated lens design
Current techniques for deep neural network (DNN) pruning often involve intricate multi-step processes that require domain-specific expertise, making their widespread adoption challenging. To address the limitation, the Only-Train-Once (OTO)…
Implicit Neural Representations (INRs) have emerged as a transformative paradigm in signal processing and computer vision, excelling in tasks from image reconstruction to 3D shape modeling. Yet their effectiveness is fundamentally limited…
We develop and experimentally validate a novel neural network design framework for silicon photonics devices that is both practical and intuitive. The framework is applicable to nearly all known integrated photonics devices, but as case…
A novel neural network (NN) approach is proposed for constrained optimization. The proposed method uses a specially designed NN architecture and training/optimization procedure called Neural Optimization Machine (NOM). The objective…
Neural networks have been employed for a wide range of processing applications like image processing, motor control, object detection and many others. Living neural networks offer advantages of lower power consumption, faster processing,…
The rational design of photonic nanostructures consists in anticipating their optical response from simple models or as variations of reference systems. This strategy is limited when different objectives are simultaneously targeted.…
Artificial Neural Networks (ANNs) were devised as a tool for Artificial Intelligence design implementations. However, it was soon became obvious that they are unable to fulfill their duties. The fully autonomous way of ANNs working,…
The alignment of optical systems is a critical step in their manufacture. Alignment normally requires considerable knowledge and expertise of skilled operators. The automation of such processes has several potential advantages, but requires…
Current methods for fabricating lenses rely on mechanical processing of the lens or mold, such as grinding, machining, and polishing. The complexity of these fabrication processes and the required specialized equipment prohibit rapid…
The increasing popularity of deep learning models has created new opportunities for developing AI-based recommender systems. Designing recommender systems using deep neural networks requires careful architecture design, and further…
Retinal image of surrounding objects varies tremendously due to the changes in position, size, pose, illumination condition, background context, occlusion, noise, and nonrigid deformations. But despite these huge variations, our visual…
Feature selection for a given model can be transformed into an optimization task. The essential idea behind it is to find the most suitable subset of features according to some criterion. Nature-inspired optimization can mitigate this…
Automatic Image Cropping is a challenging task with many practical downstream applications. The task is often divided into sub-problems - generating cropping candidates, finding the visually important regions, and determining aesthetics to…
Automatic image generation is no longer just of interest to researchers, but also to practitioners. However, current models are sensitive to the settings used and automatic optimization methods often require human involvement. To bridge…
Optical flow estimation is a well-studied topic for automated driving applications. Many outstanding optical flow estimation methods have been proposed, but they become erroneous when tested in challenging scenarios that are commonly…
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.…
In the study of nuclear cross sections, the computational demands of data assimilation methods can become prohibitive when dealing with large data sets. We have developed a novel variant of the data thinning algorithm, inspired by the…
Although the currently popular deep learning networks achieve unprecedented performance on some tasks, the human brain still has a monopoly on general intelligence. Motivated by this and biological implausibility of deep learning networks,…
Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the…
The thinnest possible camera is achieved by removing all optics, leaving only the image sensor. We train deep neural networks to perform multi-class detection and binary classification (with accuracy of 92%) on optics-free images without…