Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Active learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 757 records · Page 42

A History of Space Toxicology Mishaps: Lessons Learned and Risk Management

After several decades of human spaceflight, the community of space-faring nations has accumulated a diverse and sometimes harrowing history of toxicological events that have plagued human space endeavors almost from the very beginning. Lessons have been learned in ground-based test beds and others were discovered the hard way - when human lives were at stake in space. From such lessons one can build a risk-management framework for toxicological events to minimize the probability of a harmful exposure, while recognizing that we cannot foresee all events. Space toxicologists have learned that relatively harmless compounds can be converted by air revitalization systems into compounds that cause serious harm to the crew. Our toxic risk management strategy now includes an assessment of the fate of any compound that might be released into the atmosphere. Propellants are highly toxic compounds, yet we have not always been able to thoroughly isolate the crew from exposure to these toxicants. Leakage of fluids from systems has resulted in hazardous conditions at times, and the behavior of such compounds inside a spacecraft has taught us how to manage potentially harmful escapes should they occur. Potential combustion events are an ever-present threat to the wellbeing of the crew. Such events have been sufficiently common that we have learned that one cannot judge the health threat of a given fire by the magnitude of the event. Management of such risks demands monitoring of combustion products. In the category of unpredictable toxic events, if one assumes that fires are predictable, we can place experience with toxic microbial metabolites, upsets during repair operations, and discharges from filters that have accumulated a substantial load of pollutants in their absorption beds. Management of such events requires a broad-spectrum, real-time analytical capability to discern the identity and concentrations of pollutants if they enter the atmosphere. Adverse events are an integral part of any human activity, and the spacefaring community must learn as much as possible from mistakes and near misses.

James, John T.↗

FASTSAT-HSV01 Thermal Math Model Correlation

This paper summarizes the thermal math model correlation effort for the Fast Affordable Science and Technology SATellite (FASTSAT-HSV01), which was designed, built and tested by NASA's Marshall Space Flight Center (MSFC) and multiple partners. The satellite launched in November 2010 on a Minotaur IV rocket from the Kodiak Launch Complex in Kodiak, Alaska. It carried three Earth science experiments and two technology demonstrations into a low Earth circular orbit with an inclination of 72deg and an altitude of 650 kilometers. The mission has been successful to date with science experiment activities still taking place daily. The thermal control system on this spacecraft was a passive design relying on thermo-optical properties and six heaters placed on specific components. Flight temperature data is being recorded every minute from the 48 Resistance Temperature Devices (RTDs) onboard the satellite structure and many of its avionics boxes. An effort has been made to correlate the thermal math model to the flight temperature data using Cullimore and Ring's Thermal Desktop and by obtaining Earth and Sun vector data from the Attitude Control System (ACS) team to create an "as-flown" orbit. Several model parameters were studied during this task to understand the spacecraft's sensitivity to these changes. Many "lessons learned" have been noted from this activity that will be directly applicable to future small satellite programs.

McKelvey, Callie↗

VIIRS On-Orbit Optical Anomaly - Investigation, Analysis, Root Cause Determination and Lessons Learned

A gradual, but persistent, decrease in the optical throughput was detected during the early commissioning phase for the Suomi National Polar-Orbiting Partnership (SNPP) Visible Infrared Imager Radiometer Suite (VIIRS) Near Infrared (NIR) bands. Its initial rate and unknown cause were coincidently coupled with a decrease in sensitivity in the same spectral wavelength of the Solar Diffuser Stability Monitor (SDSM) raising concerns about contamination or the possibility of a system-level satellite problem. An anomaly team was formed to investigate and provide recommendations before commissioning could resume. With few hard facts in hand, there was much speculation about possible causes and consequences of the degradation. Two different causes were determined as will be explained in this paper. This paper will describe the build and test history of VIIRS, why there were no indicators, even with hindsight, of an on-orbit problem, the appearance of the on-orbit anomaly, the initial work attempting to understand and determine the cause, the discovery of the root cause and what Test-As-You-Fly (TAYF) activities, can be done in the future to greatly reduce the likelihood of similar optical anomalies. These TAYF activities are captured in the lessons learned section of this paper.

Iona, Glenn↗

Generalized Brønsted‐Evans‐Polanyi Relationships for Reactions on Metal Surfaces from Machine Learning

Abstract Brønsted‐Evans‐Polanyi (BEP) relationships, i. e., a linear scaling between reaction and activation energies, lie at the core of computational design of heterogeneous catalysts. However, BEPs are not general and often require reparameterization for each class of reactions. Here we construct generalized BEPs (gBEPs), which can predict activation energies for a diverse dataset of reactions of C, O, N and H containing molecules on metal surfaces. In a first step we develop a set of descriptors based on scaling relationships that can capture the change in chemical identity of reactants during the reaction. Subsequently, we use the reaction energy, these descriptors and a single descriptor for the surface structure to parameterize machine learning based regression approaches for the prediction of activation energies. The best approach we developed shows a Mean Absolute Error (MAE) of 0.11 eV for the training set (80 % of the data set) and 0.23 eV for the test set (20 % of the data set). The methodology presented here allows to calculate activation energies within fractions of seconds on a typical personal computer and due to its generality, accuracy and simplicity in application it might prove to be useful in transition metal catalyst design.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Reducing NPR 7120.5D to Practice: Transitioning from Design Reviews to the SIR Hardware Review

The Gravity Recovery And Interior Laboratory (GRAIL) mission was the first Jet Propulsion Laboratory (JPL) project initiated under NASA's revised rules for space flight project management, NPR 7120.5D, "NASA Space Flight Program and Project Management Requirements." NASA selected GRAIL through a competitive Announcement of Opportunity process and funded its Phase B Preliminary Design effort. The team's first major milestone was a JPL institutional milestone, the Project Mission System Review (PMSR), which proved an excellent tune-up for the end-of-Phase-B NASA life-cycle review, the Preliminary Design Review (PDR). Building on JPL experience on the Prometheus and Juno projects, the team successfully organized for and conducted these reviews on an aggressive schedule. For the Project Critical Design Review (CDR), lessons learned from the PDR and updated Standing Review Board (SRB) practices from the Agency were factored into the review preparation effort. Additionally, the review was held at the Principal Investigator's institution, the Massachusetts Institute of Technology, rather than at the project management center (JPL), which necessitated additional cross-country coordination steps. The PMSR, PDR, and CDR were design reviews and largely paper-oriented. For the System Integration Review (SIR), the project needed to transition to a hardware review and deal with paper in a very different manner. While many of the practices employed for the design reviews were modified and retained (e.g., review preparation team, gate products management, pre-reviews, SRB coordination), the review agenda, presentation style, and slide templates were significantly changed. A key success factor concerned the handling of project open paper, which was succinctly and effectively communicated to the SRB in presentations.This paper provides a brief overview of the GRAIL mission and its project management challenges, provides a detailed description of project SIR preparation and execution activities, including positive and negative lessons learned and identifies recommendations for future NASA (and non- NASA) project teams.

NPR 7120.5D↗

DOE FAIR Surrogate Benchmarks Supporting AI and Simulation Research (SBI Surrogate Benchmark Initiative) (Final Report)

Computational Science is being revolutionized by integrating AI and simulation and, in particular, by deep learning surrogate models that can replace all or part of traditional large‐scale HPC computations. Such surrogates can achieve remarkable performance improvements, as much as several orders of magnitude, and save both compute time and energy. The Surrogate Benchmark Initiative (SBI) project creates a community repository and FAIR (Findable, Accessible, Interoperable, and Reusable) data ecosystem for HPC application surrogate benchmarks. The SBI team comes from Argonne National Laboratory (ANL), Indiana University (IU), Rutgers University, the University of Tennessee, Knoxville (UTK), and the University of Virginia(UVA). SBI repositories include data, code, and all relevant collateral artifacts, that the science and engineering community needs to use and reuse these data sets and surrogates. SBI repositories generate active research from both participants in SBI and the broader AI and domain science communities. This project develops surrogates that use several different neural nets to learn and quickly infer the results of simulations and data systems and capture them as surrogate benchmarks with a rich set of metadata, covering. Data; Model; Metrics specification; Machine specification; Science, Speed, Power Results, We research FAIR metadata for these benchmarks. We develop application surrogate examples as benchmarks across many fields (ANL, UTK, IU, UVA). We also study non Surrogate benchmarks that have many common features and similar issues regarding FAIRness. We work with MLCommons (UVA, UTK), which is a major machine learning benchmarking activity where we get metadata ontologies, software, and benchmarks, benchmarks have datasets, models, and metadata, and they need a technical framework developed by UTK and Rutgers and deployed by UVA. We study features of Surrogates, including performance, training set size, and uncertainty quantification (Rutgers, UVA and IU).

97 MATHEMATICS AND COMPUTING↗

Subtask 1.5 – CO2 Injection Monitoring with an Optimized Scalable, Automated, Semipermanent Seismic Array

The scalable, automated, semipermanent seismic array (SASSA) method is a flexible and relatively cost-effective surface geophysical method for regular time-lapse monitoring of the movement of injected carbon dioxide (CO2) in a reservoir for CO2 enhanced oil recovery (EOR) or geologic CO2 storage operations. It has the advantages of a low-environmental-footprint while monitoring regions of a reservoir from the surface without the need for a regular grid distribution of receivers. Automated data collection is possible. As only time-lapse amplitude changes at the reservoir level due to CO2 movement within the reservoir are monitored, the turnaround time to deliver results from the SASSA method can be short, without the need for long, time-consuming data-processing workflows. As data is collected and processed, incremental information can be provided to the field operator. The Energy & Environmental Research Center (EERC) conducted a SASSA field test from September 2018 to November 2020 in a portion of the Bell Creek Field in Montana, which implemented new CO2 EOR field activities during the study period. Lessons learned from a proof-of-concept study were incorporated to improve the data quality of the SASSA method and demonstrate the viability of the technology. The EERC implemented several enhancements to improve data quality, including 1) an iterative survey design, which allowed placing the receivers in strategic locations where the movement of the CO2 in the reservoir could be tracked with minimum interference by the cultural noise in the study area; 2) the use of powerful seismic sources in the form of surface orbital vibrators, and 3) data acquisition during optimal periods. History-matched reservoir simulation was performed to predict gas saturation and pressure response induced by CO2 injection in the study area. The results were compared with the SASSA-measured responses to CO2 injection as a partial validation technique. A match between the two methods was observed for most of the SASSA points predicted to have intersected a CO2 saturation change. The validated results provide confidence that the SASSA method can be used independently as a CO2 saturation monitoring technique. As data are collected and processed, incremental information can be provided to the field operator. The critical components of the SASSA workflow for a successful application of the method are the following: Iterative survey design with information about CO2 injection activities from the oilfield operator. A detailed CO2 injection plan is the key driver to select the strategic monitoring location of the SASSA sensors. After this information is incorporated in the initial distribution of sources and receivers in the study area, high-resolution satellite images are used to identify ground locations not affected by cultural noise sources, such as power lines, pipelines/flow lines, or roadways. In the next iteration of the survey design, a scouting trip to the study area is needed to understand more details of the noise sources identified in the previous step and the intensity of the field activities that can also generate noise during the monitoring. Integrating the information from the scouting trip into the survey design to select the optimum source and receiver locations is the final step. Noise attenuation. The variety of noise types during seismic monitoring of an oil field is enormous. Tailored noise characterization and processing at a node-by-node level can enhance the performance and sensitivity of the SASSA technique. Future advancements that could improve the efficiency and application of the SASSA technology include: Gaining a better understanding of the noise field produced by the seismic source to aid the choice of receiver location. Surface noise from the source can overwhelm the small signal changes due to CO2 that the SASSA method measures. Improved data-processing workflow to automatically analyze and adapt to dynamic noise conditions associated with industrial settings. This subtask was funded through the EERC–DOE Joint Program on Research and Development for Fossil Energy-Related Resources Cooperative Agreement No. DE- FE0024233.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Adaptative Site Management for a 115 Acre Chlorinated Solvent Plume with Two Separate Source Areas at Kennedy Space Center, Florida

Background/Objectives. During Resource Conservation and Recovery Act (RCRA) Facility Investigation (RFI) activities, Geosyntec delineated a chlorinated volatile organic compound (CVOC) plume at the National Aeronautics and Space Administration’s (NASA’s) Vehicle Assembly Building (VAB) area located at KSC, Florida. The RFI activities identified an approximate 115-acre dissolved plume (primarily vinyl chloride) and a trichloroethene (TCE) source area in an active aerospace complex that is surrounded by sensitive wetland/waterbodies. Due to the size of the impacted area, the Corrective Measure Design included a multi-component strategy: (i) address the source area via bioremediation; (ii) protect sensitive wetlands from impacted groundwater discharge via biosparging; and (iii) Long Term Monitoring (LTM) of the remaining dissolved plume. After the Corrective Measures implementation (CMI), NASA and Geosyntec worked with Florida Department of Environmental Protection (FDEP) to implement an adaptive site management for the complex, 115-acre site outside of the traditional RCRA process. The adaptive site management approach relied on performing supplemental assessments and implementing Interim Measures (IMs) to further assess and implement remedies over time while working within site and budget constraints, with an overall goal of achieving enough mass reduction to transition the entire site to LTM and eventually achieve site closure. Approach/Activities. After the biosparge barrier was operational and bioremediation within the source area (referred to as Hot Spot 1) achieved the Corrective Action Objective (CAO), supplemental assessment of the area between Hot Spot 1 and the biosparge barrier was performed. The conceptual site model was updated using the supplemental assessment results and an air sparge system IM was designed to treat an approximate 1.2 acre area (referred to as Hot Spot 2). After installation of the air sparge system, supplemental assessment within the remainder of the 115-acre dissolved plume was performed and a second TCE source area was identified. The TCE source area and associated areas with elevated CVOC concentrations (referred to as Hot Spot 3) were delineated and a bioremediation IM was implemented. Also, the downgradient impacts from Hot Spot 3 were adjacent to a sensitive waterbody, and negotiations with the FDEP allowed the area to be monitored using LTM. Results/Lessons Learned. The performance of supplemental assessment activities and implementation of remedial alternatives as IMs allowed NASA to successfully address groundwater impacts over time, while working within the FDEP regulatory framework. The implementation of the CMI and multiple IMs has achieved the following goals: (i) the biosparge barrier has mitigated the potential discharge of impacted groundwater to an adjacent wetland; (ii) enhanced bioremediation within Hot Spot 1 achieved the CAO within 2 years and transitioned the area into LTM; (iii) operation of an air sparge system within Hot Spot 2 removed TCE as a constituent of concern and contributed to a reduction (approximately 43%) in the impacted groundwater area outside the air sparge treatment area (plume collapse); and (iv) bioremediation within Hot Spot 3 removed approximately 80% of the CVOC mass and contributed to a reduction (approximately 47%) in the impacted groundwater area outside the bioremediation IM treatment area. Overall, the adaptive approach is protecting the sensitive water bodies surrounding the complex site and reducing the area of impacted groundwater, which is moving the entire site towards LTM.

Rebecca C Daprato↗

Machine Learning with Gradient-Based Optimization of Nuclear Waste Vitrification with Uncertainties and Constraints

Gekko is an optimization suite in Python that solves optimization problems involving mixed-integer, nonlinear, and differential equations. The purpose of this study is to integrate common Machine Learning (ML) algorithms such as Gaussian Process Regression (GPR), support vector regression (SVR), and artificial neural network (ANN) models into Gekko to solve data based optimization problems. Uncertainty quantification (UQ) is used alongside ML for better decision making. These methods include ensemble methods, model-specific methods, conformal predictions, and the delta method. An optimization problem involving nuclear waste vitrification is presented to demonstrate the benefit of ML in this field. ML models are compared against the current partial quadratic mixture (PQM) model in an optimization problem in Gekko. GPR with conformal uncertainty was chosen as the best substitute model as it had a lower mean squared error of 0.0025 compared to 0.018 and more confidently predicted a higher waste loading of 37.5 wt% compared to 34 wt%. The example problem shows that these tools can be used in similar industry settings where easier use and better performance is needed over classical approaches. Future works with these tools include expanding them with other regression models and UQ methods, and exploration into other optimization problems or dynamic control.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

FAIR Surrogate Benchmarks Supporting AI and Simulation Research (Final Report)

Computational Science is being revolutionized by integrating AI and simulation and, in particular, by deep learning surrogate models that can replace all or part of traditional large‐scale HPC computations. Such surrogates can achieve remarkable performance improvements, as much as several orders of magnitude, and save both compute time and energy. The Surrogate Benchmark Initiative (SBI) project creates a community repository and FAIR (Findable, Accessible, Interoperable, and Reusable) data ecosystem for HPC application surrogate benchmarks. The SBI team comes from Argonne National Laboratory (ANL), Indiana University (IU), Rutgers University, the University of Tennessee, Knoxville (UTK), and the University of Virginia (UVA). SBI repositories include data, code, and all relevant collateral artifacts that the science and engineering community need to use and reuse these data sets and surrogates. SBI repositories generate active research from both the participants in SBI and the broad community of AI and domain scientists. This project develops surrogates that use several different neural nets to learn and quickly infer the results of simulations and data systems and captures them as surrogate benchmarks with a rich set of metadata covering: Data; Model; Metrics specification; Machine specification; and Science, Speed, and Power Results. We research FAIR metadata for these benchmarks. We develop application surrogate examples as benchmarks across many fields (ANL, UTK, IU, UVA). We also study non-Surrogate benchmarks that have many common features and similar issues as regards FAIRness. We work with MLCommons (UVA, UTK), which is a major machine learning benchmarking activity where we get metadata ontologies, software, and benchmarks, Benchmarks have datasets, models, and metadata and they need a technical framework developed by UTK and Rutgers and deployed by UVA. We study features of Surrogates including performance, training set size, and uncertainty quantification (Rutgers, UVA and IU).

97 MATHEMATICS AND COMPUTING↗

Lessons Learned from the Construction of Upgrades to the NASA Glenn Icing Research Tunnel and Re-activation Testing

Major upgrades were made in 1999 to the 6- by 9-Foot (1.8- by 2.7-m) Icing Research Tunnel (IRT) at the NASA Glenn Research Center. These included replacement of the electronic controls for the variable-speed drive motor, replacement of the heat exchanger, complete replacement and enlargement of the leg of the tunnel containing the new heat-exchanger, the addition of flow-expanding and flow-contracting turning vanes upstream and downstream of the heat exchanger, respectively, and the addition of fan outlet guide vanes (OGV's). This paper presents an overview of the construction and reactivation testing phases of the project. Important lessons learned during the technical and contract management work are documented.

Sheldon, David W.↗

Post-Disaster Microgrid Formation for Enhanced Distribution System Resilience

This paper proposes a deep reinforcement learning (DRL) based approach for post-disaster critical load restoration in active distribution systems to form microgrids through network reconfiguration to minimize critical load curtailments. Distribution networks are represented as graph networks, and optimal network configurations with microgrids are obtained by searching for the optimal spanning forest. The constraints to the research question being explored are the radial topology and power balance. Unlike existing analytical and population-based approaches, which necessitate the repetition of entire analyses and computation for each outage scenario to find the optimal spanning forest, the proposed approach, once properly trained, can quickly determine the optimal, or near-optimal, spanning forest even when outage scenarios change. When multiple lines fail in the system, the proposed approach forms microgrids with distributed energy resources in active distribution systems to reduce critical load curtailment. The proposed DRL-based model learns the action-value function using the REINFORCE algorithm, which is a model-free reinforcement learning technique based on stochastic policy gradients. A case study was conducted on a 33-node distribution test system, demonstrating the effectiveness of the proposed approach for post-disaster critical load restoration.

active distribution systems↗

Effect of Solvent on the Local Structure, Dynamics, and Vibrational Density of States in Sn-BEA Zeolite

Lewis acid zeolites are attractive catalysts for epoxidation and biomass valorization, as they are highly active and selective in the liquid phase and can operate at or near ambient conditions. While a rich experimental literature exists on liquid-phase Lewis acid zeolite catalysis, our understanding of the molecular organization and solvent dynamics in the vicinity of Lewis acid sites with differing metal site speciation remains limited. In this work, we investigate the molecular coordination and diffusion of two common solvents (methanol and water) around the closed and open Sn-BEA zeolite active sites using molecular dynamics simulations with a machine-learned interatomic potential trained on ab initio molecular dynamics trajectories. Molecular dynamics simulations reveal that introducing active sites significantly enhances local order in the first and second solvation shells compared to the pure silica case. For methanol, both closed and open active sites are singly coordinated, while more than two water molecules coordinate the open site. In contrast to methanol, we observed that water molecules dissociate, leading to the formation of additional Sn-OH and silanol groups away from the active site. The diffusion coefficients of water and methanol are functions of the solvent population in the pore. Here, our work provides insights into how active site speciation in Lewis acid zeolites affects solvent coordination, diffusion, and vibrational signature. This information is foundational for catalyst design and optimization of liquid-phase catalytic processes in zeolites. It also demonstrates the suitability of machine-learned interatomic potentials for modeling reactive systems, enabling sufficiently long trajectories for appropriate statistical averaging.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Hybrid-RL-MPC4CLR (Hybird-Reinforcement-Learning-Model-Predictive-Control-for-Reserve-Policy-Assisted-Critical-Load-Restoration-in-Distribution-Grids)

Hybrid-RL-MPC4CLR was developed as a hybrid controller for active distribution grid critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. The RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while the MPC models grid operations incorporating the RL policy actions (i.e., reserve requirements), renewable (wind and solar) power predictions, and load demand forecasts. The developers formulated the reserve requirement determination problem as a sequential decision-making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC simulation. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The software is developed using various software packages in Python. The MPC's optimal power flow (OPF) model is implemented using the Pyomo package, the RL simulation environment is implemented using the MPC simulation with various scenarios of renewable energy and load demand profiles and power outage beginning times, based on the OpenAI Gym framework. The RL agent training is performed using the RLlib Ray package. The RL algorithm is trained offline using historical forecasts of renewable generation and load demand profiles. Simulation analysis and performance tests are conducted using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine, and battery.

Eseye, Abinet Tesfaye↗

Back-to-back high category atmospheric river landfalls occur more often on the west coast of the United States

Abstract The catastrophic December 2022-January 2023 nine atmospheric rivers in California underscore the urgent need to better understand such high-risk weather extremes. Here we applied a machine learning clustering tool to understand the activity of atmospheric river clusters. Reanalysis results show that clusters with high density, that is the time fraction under atmospheric river conditions within a cluster, exhibit more frequent high-category atmospheric rivers, alongside an increased likelihood for extreme precipitation and severe land surface responses. The key circulation patterns of atmospheric river clusters are primarily attributed to subseasonal variability. Furthermore, the occurrence and density of atmospheric river clusters are modulated by the daily variability of the geopotential height field. Climate model projections suggest that atmospheric river clusters with higher density and higher categories will be more frequent as warming level increases. Our findings emphasize the important role of atmospheric river clusters in the development of climate adaptation and resilience strategies.

54 ENVIRONMENTAL SCIENCES↗

Role of Local Structure in the Enhanced Dynamics of Deformed Glasses

External stress can accelerate molecular mobility of amorphous solids by several orders of magnitude. The changes in mobility are commonly interpreted through the Eyring model, which invokes an empirical activation volume. Here, we analyze constant-stress molecular dynamics simulations and propose a structure-dependent Eyring model, connecting activation volume to a machine-learned field, softness. We show that stress has a heterogeneous effect on the mobility that depends on local structure through softness. The barrier impeding relaxation reduces more for well-packed particles, which explains the narrower distribution of relaxation time observed under stress.

74 ATOMIC AND MOLECULAR PHYSICS↗

QuCNN : A Quantum Convolutional Neural Network with Entanglement Based Backpropagation

Quantum Machine Learning continues to be a highly active area of interest within Quantum Computing. Many of these approaches have adapted classical approaches to the quantum settings, such as QuantumFlow, etc. We push forward this trend, and demonstrate an adaption of the Classical Convolutional Neural Networks to quantum systems - namely QuCNN. QuCNN is a parameterised multi-quantum-state based neural network layer computing similarities between each quantum filter state and each quantum data state. With QuCNN, back propagation can be achieved through a single-ancilla qubit quantum routine. QuCNN is validated by applying a convolutional layer with a data state and a filter state over a small subset of MNIST images, comparing the backpropagated gradients, and training a filter state against an ideal target state.

high performance computing, quantum computing↗

ReLU, Sparseness, and the Encoding of Optic Flow in Neural Networks

Accurate self-motion estimation is critical for various navigational tasks in mobile robotics. Optic flow provides a means to estimate self-motion using a camera sensor and is particularly valuable in GPS- and radio-denied environments. The present study investigates the influence of different activation functions—ReLU, leaky ReLU, GELU, and Mish—on the accuracy, robustness, and encoding properties of convolutional neural networks (CNNs) and multi-layer perceptrons (MLPs) trained to estimate self-motion from optic flow. Our results demonstrate that networks with ReLU and leaky ReLU activation functions not only achieved superior accuracy in self-motion estimation from novel optic flow patterns but also exhibited greater robustness under challenging conditions. The advantages offered by ReLU and leaky ReLU may stem from their ability to induce sparser representations than GELU and Mish do. Our work characterizes the encoding of optic flow in neural networks and highlights how the sparseness induced by ReLU may enhance robust and accurate self-motion estimation from optic flow.

97 MATHEMATICS AND COMPUTING↗