Standard Modules Research Articles

Completing the A2 Andrews–Schilling–Warnaar Identities

Abstract We study the Andrews–Schilling–Warnaar sum-sides for the principal characters of standard (i.e., integrable, highest weight) modules of ${\operatorname {A}}_2^{(1)}$. These characters have been studied recently by Corteel, Dousse, Foda, Uncu, Warnaar, and Welsh. We prove complete sets of identities for moduli $5$ through $8$ and $10$. The cases of moduli $6$ and $10$ are new. Our proofs use Corteel–Welsh recursions for cylindric partitions and certain relations satisfied by the Andrews–Schilling–Warnaar sum-sides. We further show that at all moduli, a complete set of conjectures may be deduced using certain explicit “seed” conjectures. These seed conjectures are obtained by appropriately truncating our conjectures for the “infinite” level. Additionally, for moduli $3k$, we use an identity of Weierstraß to deduce new sum-product identities starting from the results of Andrews–Schilling–Warnaar.

The Terwilliger algebra of symplectic dual polar graphs, the subspace lattices and Uq(sl2)

The adjacency matrix of a symplectic dual polar graph restricted to the eigenspaces of an abelian automorphism subgroup is shown to act as the adjacency matrix of a weighted subspace lattice. The connection between the latter and Uq(sl2) is used to find the irreducible components of the standard module of the Terwilliger algebra of symplectic dual polar graphs. The multiplicities of the isomorphic submodules are given.

SUSTAINABLE SHIP DESIGN WITH MODULAR SHIPBUIDLING APPROACH

The present paper outlines the approach used for the European project called NAVAIS (New, Advanced and Value-Added Innovative Ships) to reconsider the ship initial design process flow that contributes to minimize the impact on the environment. The main challenge focusses on modular design at the initial design stage, to foster re-use of standard logical modules, and digital collaboration platform technics between all actors. The core process relies on Model Based System Engineering (MBSE), moving from an Engineering To Order (ETO) conventional ship design method, to a Configuration To Order (CTO) method. Another benefit of this new approach is the ability for the class society to pre-approve the various pre-designed systems modules in advance, thus saving time during the final approval process. The overall initial design approach includes a specific attention on how a single collaborative platform can orchestrate several processes coming from different stakeholders having specific expertise. The domains covered are parametric hull form design, logical modular module design, ship resistance curve calculation, propulsion equipment prediction, ship energy efficiency and underwater radiation noise analysis. The paper presents the research work that has been achieved on that topic so far and will benefit from demos and videos that have been produced by the members of the project.

Deep Reinforcement Learning with Corrective Feedback for Autonomous UAV Landing on a Mobile Platform

Autonomous Unmanned Aerial Vehicle (UAV) landing remains a challenge in uncertain environments, e.g., landing on a mobile ground platform such as an Unmanned Ground Vehicle (UGV) without knowing its motion dynamics. A traditional PID (Proportional, Integral, Derivative) controller is a choice for the UAV landing task, but it suffers the problem of manual parameter tuning, which becomes intractable if the initial landing condition changes or the mobile platform keeps moving. In this paper, we design a novel learning-based controller that integrates a standard PID module with a deep reinforcement learning module, which can automatically optimize the PID parameters for velocity control. In addition, corrective feedback based on heuristics of parameter tuning can speed up the learning process compared with traditional DRL algorithms that are typically time-consuming. In addition, the learned policy makes the UAV landing smooth and fast by allowing the UAV to adjust its speed adaptively according to the dynamics of the environment. We demonstrate the effectiveness of the proposed algorithm in a variety of quadrotor UAV landing tasks with both static and dynamic environmental settings.

Achieving Lumbar Epidural Block Competency in Inexperienced Trainees after a Structured Epidural Teaching Model: A Randomized, Single Blind, Prospective Comparison of CUSUM Learning Curves

Aim The aim of this randomized, prospective study was to investigate whether the use of the structured epidural teaching model (SETM) may affect the learning curve for lumbar epidural block in novice trainees when compared with a standard teaching module. Introduction There is a paucity of literature regarding the efficacy of teaching epidural blocks and comparisons between the different educational approaches. Method Forty-four PGY3 anesthesia trainees were randomized to receive (study group) or to not receive (control group) the SDM (structured didactic model) before the beginning of their 6 months clinical practice rotation in labor and delivery suites. A CUSUM learning curve was built for every trainee. The scores were assigned by the staff instructor, who was unaware of the group to which the trainee belonged. Results The number of subjects who achieved an improvement in performance was 8 trainees from the control group and 14 from the study group. The probability of achieving an improvement was higher (p < 05) in the study group than in the control group, with an aOR of 3.25 (CI: 1.01; 12.1). The proportion of subjects in the study group who completed the epidural without help was 1.21 (1.05–1.41) times the proportion of subjects who completed the epidural without help in the control group. The probability of completing the epidural block without any assistance was 21% higher in the study group than in the control group (p < 05). Conclusion We have demonstrated that the use of the structured epidural teaching model (SETM) may improve the learning curve (CUSUM) for lumbar epidural block in novice, entirely inexperienced, anesthesia trainees.

The generalized injectivity conjecture

We prove a conjecture of Casselman and Shahidi stating that the unique irreducible generic subquotient of a standard module is necessarily a subrepresentation for a large class of connected quasi-split reductive groups, in particular for those which have a root system of classical type (or product of such groups). To do so, we prove and use the existence of strategic embeddings for irreducible generic discrete series representations, extending some results of Moeglin.

In-Field Energy Performance of Solar PV Module Made of UMG Silicon

Upgraded metallurgical grade silicon (UMG-Si) PV modules have failed to make their space in the PV market, which was partly to the uncertainty on their in-field performance that brings the wide disparity of results published over the years. The most-recently developed UMG-Si PV modules have demonstrated similar initial degradation and efficiencies under standard test conditions (STC) to those obtained with conventional solar grade silicon (SoG-Si). Nevertheless, their performance under operating conditions other than STC and its impact on the energy production are key aspects that have not yet been properly characterized in the literature. This article analyzes the in-field performance of a PV generator comprised of recently developed UMG-Si modules. This performance was compared to that of another PV generator comprising standard polysilicon modules. The cells and modules of both types of generators were made by the same manufacturer in the same period and on the same production lines, which guarantees that performance differences encountered are exclusively due to the silicon employed. Contrary to the previous experience, this article reveals that UMG-Si modules do not necessarily present a better temperature performance than today's conventional modules. The analyzed UMG-Si modules presented 1.6% less efficiency under low irradiance conditions, but this different irradiance performance led to an insignificant difference (less than 0.5%) in their energy production. No significant degradation was measured in both UMG-Si and SoG-Si modules during the two-year analyzed period, being the final energy performance of both types of modules essentially the same. These results can be considered as highly representative of the current state-of-the-art of UMG-Si technology.

Addressing functionalities of agricultural robotic (agribots) and automation in the agriculture practices: What’s next?

This paper presents and explores the functionalities of automation and agricultural robotics (agribots) in recent years for agricultural operations. The explicit challenges fronting agribots and automation with regards to the operative implementation of Industry 4.0 are discussed. In this paper, several research works and developments on automation and agribots from different scopes and field areas are reviewed to explore recent agricultural practices. The first technology is on the automation work on developing a control algorithm that uses a single sensor that could recognise landmarks in the row-type plantation environment. This is followed by the navigation of a vehicle using a laser range finder (LRF) to a point-to-go aim location in the plantation by generating a control algorithm equipped with a sensor for an autonomous agricultural vehicle to detect the landmarks in the row-type plantation setting. The second technology is related to an automation device by developing an automated detector and counter (Oto-BaCTM) for bagworm census using deep learning with a Faster Regional Convolutional Neural Network (Faster R-CNN) and normal camera. Meanwhile the third technology is related to agribots via the design and development of a fully automated Agriculture robot (Agribot) for harvesting underground plants (rhizomes) with the assistance of transmission and receiving parts using microcontroller software. Another agribot technology would be on the development of Thorvald II agricultural robotic system, utilising a modularity hardware whereby the robot consists of standard modules and can be reconstructed to handle tasks in various types of environments. The first automation technology results showed the performance of the navigation systems to operate the tractor autonomously along the test path without any crashes on the guide cones. The second automation technology on the Oto-BaCTM performance, produced a positive Pearson product-moment correlation coefficient between the two variables (percentages of detection and temperature), R2 = 0.997 and p = 0.02 for Trial 1 and R2 = 0.888 and p = 0.04 for Trial 2. Meanwhile, the third technology on the Agribot, successfully picked up the rhizome plants, sprayed pesticides, and traced of the soil moisture content. Finally, the last automation technology which was on the development of Thorvald II, came out with positive results on the pass traction test, all&#x0D; obstacles, and the incline test. The harvesting robot detected the ripe tomatoes at a 95% success rate by implementing the self-developed algorithm that applied the Adaboost and APV classifiers. However, a 5% miss detection occurred due to the leaf obstruction. The multi-robot system can be designed to handle pest control tasks via UAVs and UGVs. For weed patch recognition, the developed algorithms showed their robustness by precisely distinguishing and mapping the crop rows with a 100% accuracy, while the inter-row weed patches with an accuracy of 85%, and it was proposed to detect the early growth stage based on the weed maps through site-specific weed management. By implementing a 3D fruit detection algorithm, the precision for pepper, eggplant, and guava datasets was 0.864, 0.886, and 0.888, while the recall dataset was 0.889, 0.762, and 0.812, respectively. The proposed algorithm was effective and robust; hence it is appropriate to be applied as an agricultural harvesting robot. A roadmap in applying swarm robotics is described towards the weed control problems and is being implemented within the Swarm Robotics for Agricultural Applications scope. Thus, a baseline result was introduced specifically for monitoring and mapping out weeds in a field via a swarm of UAVs. Hence, the impact on the use of agribots and automation technologies is the realization of a more efficient systems potential to be operated in safe conditions and are cost effective for the farmers, allowing farmers to focus more on improving overall production yields. As a recommendation, there is a need for research and development of multipurpose and adaptive algorithms to be incorporated into different sensor platforms.

Assessment of prototype lightweight photovoltaic modules after over 1-year field test in Polish conditions

The compliance with international standards does not necessarily ensure a long-term reliability of photovoltaic modules. Field tests are required to make the standard tests more adjusted to the evaluation of new concepts. Numerous researches focus on long-term performance of standard modules, but only few studies are dedicated to lightweight modules. Therefore, the field operation of a PV system consisting of 28 lightweight modules of 4 different types (denoted as P1, P2, P3 and P4) has been being monitored for a year in warm temperate climate conditions. Over this period, the modules were tested by visual inspection, thermography and electroluminescence imaging and their electrical parameters were measured to compare results with the outcome of simulations in PVsyst. Visual inspections revealed yellowing and delamination of a few P2 and P4 modules because of issues with EVA foil. Thermography exposed many hot spots and failure of substrings in case of P2 modules. Also, the electroluminescence imaging showed numerous defects, mostly various micro cracks, which affected all modules’ types. Nevertheless, excluding P2 modules, the others generated higher yield than estimated by the simulations. Analysing year-to-year degradation, results for P3 and P4 were in line with results predicted for standard PV modules in similar climates.

Point-of-care ultrasound educational interventions in the neonatal intensive care unit: A systematic review.

The benefits of point-of-care ultrasound (POCUS) in the neonatal intensive care unit (NICU) have been widely recognized, but education on this area of practice remains variable. We reviewed published educational interventions regarding POCUS use in the NICU and whether they have led to sustainable increases in POCUS use. A systematic search of 6 databases was performed for publications from January 2000 to March 2021. Studies with quantitative data related to POCUS educational interventions in the NICU were included. Data on number of participants and roles, educational intervention, curriculum description, and project outcome measures (including sustainability) was extracted. The search resulted in 686 articles, of which nine studies met the inclusion criteria. Educational interventions included didactic sessions, simulation practice, animal practice, and practice in real patients. The most common assessment was based on the quality and accuracy of the images. At the participant level, the average time to reach proficiency ranged from eight hours and thirty-six minutes to five months, and none of the studies evaluated sustainability of POCUS use after the intervention. There is a lack of standardized training modules and assessments for POCUS use in the NICU. Given that none of the studies addressed sustainability or standardized training, we recommend that a standardized training protocol and assessment tool is developed and studied longitudinally; and that barriers to sustainable POCUS use in the NICU (such as billing issues and a lack of POCUS machines and instructors) be systematically addressed as part of this work.

Rapid diagnosis of Plasmodium falciparum malaria using a point-of-care loop-mediated isothermal amplification device.

LAMP diagnosis of malaria is simple and cost-effective with acceptable sensitivity and specificity as compared to standard diagnostic modules such as microscopy, RDTs and nested PCR, and thus its deployment for onsite screening of malaria in resource-limited regions is under consideration. However, the requirement of an electricity-operated dry bath and bulky read-out unit is still a major concern. In an effort to simplify this limitation, we have developed a portable LAMP device and fluorescence readout unit which can be used in the rapid point-of-care diagnosis of malaria. We have developed a point-of-care diagnostic LAMP device that is easy to operate by a mobile application, and the results can be quantified with a fluorescent readout unit. The diagnostic performance of the device was evaluated in 90 P. falciparum-infected clinical isolates stored at 4°C for 6-7 years and 10 freshly collected isolates from healthy volunteers. The LOD and quantitative ability of LAMP in estimating parasitemia levels were revealed with laboratory-grown P. falciparum strain (3D7). The LAMP assay performed in our device was exclusive for P. falciparum detection with sensitivity and specificity determined to be 98.89% and 100%, respectively, in clinical isolates. The LOD was documented to be 1 parasite/µl at the cut-off ADC value of 20. Parasite density estimated from ADC values showed concordance with microscopically determined parasite density of the cultured P. falciparum 3D7 strain. The LAMP assay performed in our device provides a possible portable platform for its deployment in the point-of-care diagnosis of malaria. Further validation of the quantitative ability of the assay with freshly collected or properly stored clinical samples of known parasitemia is necessary for field applicability.

Aging investigation of the latest standard dual power modules using improved interconnect technologies by power cycling test

The latest standard “New Dual” power module has been developed for both silicon and silicon-carbide devices to meet the increasing demands in high reliability and high temperature power electronic applications. Due to the new package is just starting to release on the market, the reliability performance has not been fully studied. This paper investigates the power cycling capabilities of a 1.7 kV/1.8 kA IGBT power module based on the new package. Both the electrical and thermal performances have been studied before and after the power cycling. Neither the chips nor bond wires have noticeable degradation after 1.2 million cycles with ΔTj = 100 K and Tjmax = 150 °C. Nevertheless, the end-of-life criterion of an increased conduction voltage (Vce) in the test environment has been reached at about 600 k cycles. The further scanning acoustic microscopy test unveils that the fatigue site shifts from the conventional near-to-die interconnect (e.g., bond wire lift-offs) to the direct bond copper (DBC) substrate and baseplate layers. Considering the new package has more than ten times cycle life than the traditional power module, it expects the thermo-mechanical fatigue is not the life-limiting mechanism with further improved interconnect technologies. Meanwhile, as the previous bottlenecks (e.g., bond wires) are addressed, some new fatigue mechanisms, e.g., delamination of the DBC, become visible in this new package.

Optimal design of high frequency high efficiency and high‐power density DC–DC power module based on GaN

AbstractThis paper develops a railway power module with wide range voltage (dc 60—dc 160 V) input and constant voltage output (24 V/10 A) . The power module adopts a two‐stage topology structure to realize voltage conversion. Use the most advanced GaN (gallium nitride) as the main power switching devices. The first stage circuit architecture uses a two‐phase interleaved buck converter convert the wide range input voltage into a constant intermediate bus voltage (48 V) through closed‐loop control, and then the LLC resonant converter converts the intermediate bus voltage (dc 48 V) into a constant output voltage (dc 24 V) through open‐loop control, and realize the primary side and secondary side dc 3000 V electrical isolation. This article from the circuit topology, the power devices selection, buck converter magnetic integrated coupling inductance design, planar magnetic integration LLC resonant transformer optimization design has carried on the detailed discuss and analysis. All circuits are integrated in a standard quarter power brick module, the final prototype can reach 96.1% peak efficiency, the power density can reach 185 W/in.3.

Prediction of Urban Taxi Travel Demand by Using Hybrid Dynamic Graph Convolutional Network Model

The efficient and accurate prediction of urban travel demand, which is a hot topic in intelligent transportation research, is challenging due to its complicated spatial-temporal dependencies, dynamic nature, and uneven distribution. Most existing forecasting methods merely considered the static spatial dependencies while ignoring the influence of the diversity of dynamic demand patterns and/or uneven distribution. In this paper, we propose a traffic demand forecasting framework of a hybrid dynamic graph convolutional network (HDGCN) model to deeply capture the characteristics of urban travel demand and improve prediction accuracy. In HDGCN, traffic flow similarity graphs are designed according to the dynamic nature of travel demand, and a dynamic graph sequence is generated according to time sequence. Then, the dynamic graph convolution module and the standard graph convolution module are introduced to extract the spatial features from dynamic graphs and static graphs, respectively. Finally, the spatial features of the two components are fused and combined with the gated recurrent unit (GRU) to learn the temporal features. The efficiency and accuracy of the HDGCN model in predicting urban taxi travel demand are verified by using the taxi data from Manhattan, New York City. The modeling and comparison results demonstrate that the HDGCN model can achieve stable and effective prediction for taxi travel demand compared with the state-of-the-art baseline models. The proposed model could be used for the real-time, accurate, and efficient travel demand prediction of urban taxi and other urban transportation systems.

A randomized controlled trial of customized adherence enhancement (CAE-E): study protocol for a hybrid effectiveness-implementation project

BackgroundMood-stabilizing medications are a cornerstone of treatment for people with bipolar disorder, though approximately half of these individuals are poorly adherent with their medication, leading to negative and even severe health consequences. While a variety of approaches can lead to some improvement in medication adherence, there is no single approach that has superior adherence enhancement and limited data on how these approaches can be implemented in clinical settings. Existing data have shown an increasing need for virtual delivery of care and interactive telemedicine interventions may be effective in improving adherence to long-term medication.MethodsCustomized adherence enhancement (CAE) is a brief, practical bipolar-specific approach that identifies and targets individual patient adherence barriers for intervention using a flexibly administered modular format that can be delivered via telehealth communications. CAE is comprised of up to four standard treatment modules including Psychoeducation, Communication with Providers, Medication Routines, and Modified Motivational Interviewing. Participants will attend assigned module sessions with an interventionist based on their reasons for non-adherence and will be assessed for adherence, functioning, bipolar symptoms, and health resource use across a 12-month period. Qualitative and quantitative data will also be collected to assess barriers and facilitators to CAE implementation and reach and adoption of CAE among clinicians in the community.DiscussionThe proposed study addresses the need for practical adherence interventions that are effective, flexible, and designed to adapt to different settings and patients. By focusing on a high-risk, vulnerable group of people with bipolar disorder, and refining an evidence-based approach that will integrate into workflow of public-sector care and community mental health clinics, there is substantial potential for improving bipolar medication adherence and overall health outcomes on a broad level.Trial registrationThe study was registered on ClinicalTrials.gov NCT04622150 on November 9, 2020.

Polarization insensitive efficient ultra-narrow diode laser strictly locked by a Faraday filter.

A Faraday anomalous dispersion optical filter (FADOF) could lock high-power diode lasers to atomic resonance lines with ultra-narrow bandwidth. However, the polarization sensitivity of the Faraday filter limits its applications since the standard diode module often employs polarization combination to increase pumping brightness. We proposed a polarization-insensitive mutual injection configuration to solve this problem and locked a standard polarization combined diode module to Rb D2-line. The laser bandwidth was narrowed from 4 nm to 0.005 nm (2.6 GHz, FWHM) with 38.3 W output and an external cavity efficiency of 80%. This FADOF-based polarization-insensitive external-cavity scheme would find many applications, such as high energy atomic gas laser pumping (alkali lasers, metastable rare gas lasers) and quantum optics, etc.

Sensor Accuracy Analysis on Incubator Analyzer to Measure Noise and Airflow Parameters

Infant incubators are equipment to maintain a stable body temperature for premature babies. Premature babies need room conditioning that is close to conditions in the womb. Room conditioning is carried out in a baby incubator by providing a stable temperature, relative humidity, and measured air flow. This parameter must be controlled so as not to exceed the threshold that will harm the baby. Periodic calibration should be applied to the infant incubator to monitor its function. To ensure the availability of baby incubators according to service standards, it is necessary to conduct test (calibrate) using an incubator analyzer. The purpose of this study is to conduct further research on the incubator analyzer that focuses on discussing the accuracy of noise and airflow sensors with the gold standard. In this study, an experiment was carried out for the sensitivity level of several sensors that had been treated by giving treatment to sensors to choose sensors with good sensitivity to be assembled into one in the incubator analyzer module. The noise sensors (KY-037 and Analog Sound Sensor V2.2) were further compared with the values ​​on the sound level meter and the airflow sensor (D6F-V03A1) was compared with the anemometer. Sensors whose values ​​are close to the comparison values ​​were selected to be integrated into the incubator analyzer module. The incubator analyzer module used Arduino Mega2560 as a data processor and was equipped with an SD Card for the data storage. The built incubator analyzer module was also compared to the Fluke INCU II gold standard for data analysis. The results showed that the Analog Sound Sensor V2.2 had the highest error value (-4.6%) at 32°C and the D6F-V03A1 had the ability to measure sensitivity, where the results were more accurate than INCU II. Based on the error value of the noise sensor, the V2.2 sensor can be applied to measure noise in the baby incubator and the D6F-V03A1 airflow sensor produced an accuracy of up to 3 digits behind the comma which is more accurate than the standard module. The results of the INCU analyzer from this study can be used to calibrate the baby incubator, so that the certainty of the feasibility of the baby incubator is guaranteed. This research can be used as a reference for other researchers who will develop research on incubator analyzers in the future.

ConvUNeXt: An efficient convolution neural network for medical image segmentation

Recently, ConvNeXts constructing from standard ConvNet modules has produced competitive performance in various image applications. In this paper, an efficient model based on the classical UNet, which can achieve promising results with a low number of parameters, is proposed for medical image segmentation. Inspired by ConvNeXt, the designed model is called ConvUNeXt and towards reduction in the amount of parameters while retaining outstanding segmentation superiority. Specifically, we firstly improved the convolution block of UNet by using large convolution kernels and depth-wise separable convolution to considerably decrease the number of parameters; then residual connections in both encoder and decoder are added and pooling is abandoned via adopting convolution for down-sampling; during skip connection, a lightweight attention mechanism is designed to filter out noise in low-level semantic information and suppress irrelevant features, so that the network can pay more attention to the target area. Compared to the standard UNet, our model has 20% fewer parameters, meanwhile, experimental results on different datasets show that it exhibits superior segmentation performance when the amount of data is scarce or sufficient. Code will be available at https://github.com/1914669687/ConvUNeXt.

Immunity benefits of yoga and physical exercises in the era of COVID-19 Pandemic

Purpose. The novel coronavirus is the recently emerged disease of the respiratory system for which various national and international research agencies are putting joint efforts towards finding a permanent cure. Recently, the vaccine against coronavirus has been designed by various pharmaceutical agencies that are currently undergoing clinical trials. Since vaccines prevent infection by strengthening the defense system of the body, we proposed that yoga and physical exercises could act as an integrative approach to synergize the immunogenic response of the coronavirus vaccine. Yoga and physical exercises are already known to boost immunity against several other infections.&#x0D; Materials and Methods. In the present review article, we aimed towards exploring the role of yoga and physical exercise as an immunity booster against coronavirus infection. Being India is a low-income country, yoga and physical exercises could be an excellent cost-effective strategy that could be administrated along with vaccine trials to enhance immunity against virus infection.&#x0D; Results. In the present review, we analyze the studies conducted to date focusing on finding the role of yoga and physical exercises to prevent coronavirus infection. We also described the potential exercises, which are already known to enhance the immunity of the body by particularly targeting respiratory disease.&#x0D; Conclusion. The present review article will help in providing the health agencies potential targets, which could further be explored to established a standard exercise module to enhance the vaccine-mediated immunity against coronavirus infection.

Only-train-electrical-to-optical-conversion (OTEOC): simple diffractive neural networks with optical readout.

Machine learning hardware based on optical diffraction is emerging as a new computing platform with high throughput and low latency. The current all-optical diffractive deep neural networks often suffer from complex optical configuration, lack of efficient optical nonlinear activation, and critical alignment between optical layers for system integration. The opto-electronic diffractive neural networks can partially address these issues by shifting some computation load, e.g., nonlinear activation and adaptive training, to the electronic domain. However, these hybrid networks require extra optical-to-electrical conversion that inevitably slows the overall process down. Here, we propose a simple opto-electronic diffractive neural network with just one optical layer enabled by a standard phase-only spatial light modulator. The proposed system can classify images by optical readout and does not need to collect the light distribution for subsequent electronic computation. The nonlinear function is intrinsically integrated in the essential encoding process from the electronic input to the modulated wavefront of light. Thanks to its simplicity, the system can reach high classification accuracy without calibration and can be reconfigured by updating the weights without changing or moving any physical component. We believe this technology brings diffractive neural networks a step closer to building realistic optics-based neurocomputers.