Ensemble learning of diffractive optical networks

A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine learning.Specifically,there has been a revival of interest in optical computing hardware due to its potential advantages for machine learning tasks in terms of parallelization,power efficiency and computation speed.Diffractive deep neural networks(D²NNs)form such an optical computing framework that benefits from deep learning-based design of successive diffractive layers to all-optically process information as the input light diffracts through these passive layers.D²NNs have demonstrated success in various tasks,including object classification,the spectral encoding of information,optical pulse shaping and imaging.Here,we substantially improve the inference performance of diffractive optical networks using feature engineering and ensemble learning.After independently training 1252 D²NNs that were diversely engineered with a variety of passive input filters,we applied a pruning algorithm to select an optimized ensemble of D²NNs that collectively improved the image classification accuracy.Through this pruning,we numerically demonstrated that ensembles of N=14 and N=30 D²NNs achieve blind testing accuracies of 61.14±0.23%and 62.13±0.05%,respectively,on the classification of GFAR-10 test images,providing an inference improvennent of>16%compared to the average performance of the individual D²NNs within each ensemble.These results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset and might provide a significant leap to extend the application space of diffractive optical image classification and machine vision systems.     

Functional copolymer/organo-MMT nanoarchitectures: self-assembled core-shell morphology of poly(maleic anhydride-alt-α-olefin)/organo-MMT nanocomposites

This work describes the TEM morphology analysis of amphiphilic alternating copolymers of maleic anhydride (MA) with different α-olefins (1-hexene, 1-octene, 1-dodecene) synthesized by radical-initiated intercalative copolymerization of preintercalated MA···organoclay complexes in the presence of two types of organoclay such as reactive octadecyl amine-montmorillonite (ODA-MMT) and nonreactive dimethyldidodecyl ammonium-MMT (DMDA-MMT). TEM analyses of all the nanocomposites indicate the formation of symmetric or non-symmetric core-shell morphologies. Energy dispersive X-ray spectroscopy analyses were used to study the occurrence of the element in the poly(MA-alt-α-olefin)/organo-montmorillonite nanocomposites. A role of surfactant in these nanosystems insists on alternating copolymer segments with given hydrophobic/hydrophilic balance and surface organo-modifiers of MMT clays. Highly organized self-assembly with symmetric core-shell morphology were formed in nanosystems prepared in the presence of DMDA-MMT clay as compared with ODA-MMT clay-containing nanosystems. The relatively long branched olefin fragments significantly improve image parameters of core-shell morphology where some of the core structures contain accumulated and finely dispersed silicate particles at nano level around 2–25 nm. This observed phenomenon has brought a new approach for future utilization of these nanosystems in controlled drug delivery and anticancer applications with essentially prolonged activity.     

A framework for rapid visual image search using single-trial brain evoked responses

We report the design and performance of a brain computer interface for single-trial detection of viewed images based on human dynamic brain response signatures in 32-channel electroencephalography (EEG) acquired during a rapid serial visual presentation. The system explores the feasibility of speeding up image analysis by tapping into split-second perceptual judgments of humans. We present an incremental learning system with less memory storage and computational cost for single-trial event-related potential (ERP) detection, which is trained using cross-session data. We demonstrate the efficacy of the method on the task of target image detection. We apply linear and nonlinear support vector machines (SVMs) and a linear logistic classifier (LLC) for single-trial ERP detection using data collected from image analysts and naive subjects. For our data the detection performance of the nonlinear SVM is better than the linear SVM and the LLC. We also show that our ERP-based target detection system is five-fold faster than the traditional image viewing paradigm.