Search NASA⌕ Search

SEARCH · Search NASA

Results for “Contrastive 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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Particle hit clustering and identification using point set transformers in liquid argon time projection chambers

Liquid argon time projection chambers are often used in neutrino physics and dark-matter searches because of their high spatial resolution. The images generated by these detectors are extremely sparse, as the energy values detected by most of the detector are equal to 0, meaning that despite their high resolution, most of the detector is unused in a particular interaction. Instead of representing all of the empty detections, the interaction is usually stored as a sparse matrix, a list of detection locations paired with their energy values. Traditional machine learning methods that have been applied to particle reconstruction such as convolutional neural networks (CNNs), however, cannot operate over data stored in this way and therefore must have the matrix fully instantiated as a dense matrix. Operating on dense matrices requires a lot of memory and computation time, in contrast to directly operating on the sparse matrix. We propose a machine learning model using a point set neural network that operates over a sparse matrix, greatly improving both processing speed and accuracy over methods that instantiate the dense matrix, as well as over other methods that operate over sparse matrices. Compared to competing state-of-the-art methods, our method improves classification performance by 14%, segmentation performance by more than 22%, while taking 80% less time and using 66% less memory. Compared to state-of-the-art CNN methods, our method improves classification performance by more than 86%, segmentation performance by more than 71%, while reducing runtime by 91% and reducing memory usage by 61%.

calibration and fitting methods↗
NASA NTRS1989

The Marr and Albus Theories of the Cerebellum: Two Eary Models of Associative Memory

The Marr and Albus theories of the cerebellum are compared and contrasted. They are shown to be similar in their analysis of the function of the mossy fibers, granule cells, Golgi cells, and Purkinje cells. They both predict motor learning in the parallel fiber synapses on the Purkinje dendrites mediated by concurrent climbing fiber input. This prediction has been confirmed by experimental evidence. In contrast, Marr predicts these synapses would be facilitated by learning, while Albus predicts they would be weakened. Experimental evidence confirms synaptic weakening.

Albus, James S.↗
DOE OSTI2022

Model Assumptions and Data Characteristics: Impacts on Domain Adaptation in Building Segmentation

Studies on domain adaptation (DA) for remote sensing (RS) imagery analysis lack consistency in selection and description of evaluation scenarios. Without properly characterizing datasets, model assumptions, and evaluation scenarios, it is difficult to objectively compare DA methods and reach conclusions about their suitability across different applications. With this motivation, this work seeks to empirically assess to which extent the interaction between data characteristics and model assumptions influences the effectiveness of DA methods. Using the widely explored task of building footprint segmentation as a case study, we perform a large-scale study across over 200 DA scenarios that include variations across view angles, areas observed, and sensors used for data acquisition. Rather than adopting different model architectures or optimization criteria, we contrast the performances of two DA methods based on adversarial learning that differ only in their assumptions about source and target domains. Informed by metadata and data characteristics unveiled using traditional computer vision (CV) techniques as well as pretrained deep models, we provide a detailed meta-analysis of experiments highlighting the importance of accurately considering data assumptions for DA in RS segmentation tasks. As demonstrated by a “cherry-picking” exercise, different claims regarding which model is best could be made by selecting different subsets of evaluation scenarios. While well-calibrated assumptions can be beneficial, mismatching assumptions can lead to negative biases in DA applications. Furthermore, this study intends to motivate the community toward more consistent evaluation protocols while providing recommendations and insights toward creating novel benchmark datasets, documenting data characteristics, application-specific knowledge, and model assumptions.

42 ENGINEERING↗
DOE OSTI2025

CRCNS US-France Research Proposal: Collaborative Research: Encoding reward expectation in Drosophilia

The fruit fly Drosophila melanogaster has been a valuable model for investigating the genetic and neural bases that underlie learning and memory. Early and most current studies use basic behavior conditioning protocols to study learning in controlled laboratory settings. More recently, the ability to transgenically manipulate many of the brain neurons in the fruit fly with exquisite specificity, and the recent knowledge of the synaptic ‘connectome’ of the fruit fly brain, makes these animals almost unique as a comprehensive model for studies of learning, memory and motivated behavior. In fact, the connectome has revealed many types of new connections that had until now been overlooked. Within this context, the thesis of this proposal is that studies of learning and memory will be greatly enhanced by using more sophisticated means for evaluating memory representations, such as have been developed in vertebrates, and combining those studies with information from the connectome guided by computational modelling. We propose to push beyond the boundaries of existing conditioning protocols for fruit flies to investigate more complex memory representations. In particular, we will investigate the function of reinforcement pathways in relation to the absence of expected reinforcement. More specifically, we propose a series of experiments designed to investigate the memory representations in fruit flies when an expected consequence of a Conditioned Stimulus (CS) fails to occur. Although studies have evaluated how this failure can establish extinction memory for the CS, our studies will go beyond studying extinction. Specifically, we predict that in Drosophila when a CS is associated with a failed expectation of an appetitive food reinforcement it will acquire aversive value, and vice versa for a failed expectation of an aversive reinforcer. We combine these studies with manipulations of reinforcement pathways in the CNS inspired from the connectome, iteratively knitted in with established computational models. Intellectual Merit: The concept of reinforcement expectation and incentive contrast have been influential in the development of studies of associative learning in mammals. These questions are particularly challenging to answer in vertebrates because they require exquisite cellular, temporal, and genetic specificity of experimental manipulations. The recent development of work with identified neurons and their connectomes makes the larval and adult fly brains ripe as models for pushing our understanding of neural bases for these higher- order conditioning phenomena. Broader Impacts: Public health: These analyses and the conceptual framework of prediction error processing underlying them have a profound impact on our understanding of reinforcement-related behavior in humans, including monetary rewards and the mnemonic consequences of traumatic experiences, and for pathologies of the dopamine reinforcement system. Educational: This project will provide interdisciplinary training for postdoctoral researchers, Ph.D. and undergraduate students. The PIs will act as co-supervisors or mentors of students working in the different labs via face-to-face and internet-based technologies. We will also work with ASU’s award-winning Ask- A-Biologist program. This is an online science program designed to enrich the learning experiences of students of all ages and to provide classroom material for use by K-12 teachers. We will develop an extension of a game developed under a prior NSF award, and the new game will include modules to teach K-12 students about how insects learn. We will also integrate into the AAB site a program developed by a collaborator (B Gerber) at the Leibniz Institut für Neurobiologie, Magdeburg, and now in use in schools in Germany, to teach K-12 students how to train animals using the fruit fly larval learning paradigm. Underrepresented groups: All PIs will work with their university offices of Academic Diversity and Equal Opportunity for reaching underrepresented students.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2021

Exploring Sentinel-1 and Sentinel-2 diversity for Flood inundation mapping using deep learning

Identification of flood water extent from satellite images has historically relied on either synthetic aperture radar (SAR) or multi-spectral (MS) imagery. MS sensors are limited to cloud free conditions, whereas SAR imagery is plagued by noise-like speckle. Prior studies that use combinations of MS and SAR data to overcome individual limitations of these sensors have not fully examined sensitivity of flood mapping performance to different combinations of SAR and MS derived spectral indices or band transformations in color space. This study explores the use of diverse bands of Sentinel 2 (S2) through well-established water indices and Sentinel 1 (S1) derived SAR imagery along with their combinations to assess their capability for generating accurate flood inundation maps. The robustness in performance of S-1 and S-2 band combinations was evaluated using 446 hand labeled flood inundation images spanning across 11 flood events from Sen1Floods11 dataset which are highly diverse in terms of land cover as well as location. A modified K-fold cross validation approach is used to evaluate the performance of 32 combinations of S1 and S2 bands using a fully connected deep convolutional neural network known as U-Net. Our results indicated that usage of elevation information has improved the capability of S1 imagery to produce more accurate flood inundation maps. Compared to a median F1 score of 0.62 when using only S1 bands, the combined use of S1 and elevation information led to an improved median F1 score of 0.73. Water extraction indices based on S2 bands have a statistically significant superior performance in comparison to S1. Among all the band combinations, HSV (Hue, Saturation, Value) transformation of S2 bands provides a median F1 score of 0.9, outperforming the commonly used water spectral indices owing to HSV’s transformation’s superior contrast distinguishing abilities. Additionally, U-Net algorithm was able to learn the relationship between raw S2 based water extraction indices and their corresponding raw S2 bands, but not of HSV owing to relatively complex computation involved in the latter. Results of the paper establishes important benchmarks for the extension of S1 and S2 data-based flood inundation mapping efforts over large spatial extents.

Goutam Konapala↗
DOE OSTI2023

Unsupervised machine learning discovery of structural units and transformation pathways from imaging data

We show that unsupervised machine learning can be used to learn chemical transformation pathways from observational Scanning Transmission Electron Microscopy (STEM) data. To enable this analysis, we assumed the existence of atoms, a discreteness of atomic classes, and the presence of an explicit relationship between the observed STEM contrast and the presence of atomic units. With only these postulates, we developed a machine learning method leveraging a rotationally invariant variational autoencoder (VAE) that can identify the existing molecular fragments observed within a material. The approach encodes the information contained in STEM image sequences using a small number of latent variables, allowing the exploration of chemical transformation pathways by tracing the evolution of atoms in the latent space of the system. The results suggest that atomically resolved STEM data can be used to derive fundamental physical and chemical mechanisms involved, by providing encodings of the observed structures that act as bottom-up equivalents of structural order parameters. The approach also demonstrates the potential of variational (i.e., Bayesian) methods in the physical sciences and will stimulate the development of more sophisticated ways to encode physical constraints in the encoder–decoder architectures and generative physical laws and causal relationships in the latent space of VAEs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Modeling of Peptides with Classical and Novel Machine Learning Force Fields: A Comparison

The replacement of classical force fields (FFs) with novel neural-network-based frameworks is an emergent topic in molecular dynamics (MD) simulations. In contrast to classical FFs, which have proven their capability to provide insights into complex soft matter systems at an atomistic resolution, the machine learning (ML) potentials have yet to demonstrate their applicability for soft materials. However, the underlying philosophy, which is learning the energy of an atom in its surrounding chemical environment, makes this approach a promising tool. In particular for the exploration of novel chemical compounds, which have not been considered in the original parametrization of classical FFs. In this article, we study the performance of the ANI-2x ML model and compare the results with those of two classical FFs, namely, CHARMM27 and the GROMOS96 43a1 FF. We explore the performance of these FFs for bulk water and two model peptides, trialanine and a 9-mer of the α-aminoisobutyric acid, in vacuum and water. The results for water describe a highly ordered water structure, with a structure similar to those using ab initio molecular dynamics simulations. The energy landscape of the peptides described by Ramachandran maps show secondary structure basins similar to those of the classical FFs but differ in the position and relative stability of the basins. Details of the sampled structures show a divergent performance of the different models, which can be related either to the short-ranged nature of the ML potentials or to shortcomings of the underlying data set used for training. These findings highlight the current state of the applicability of ANI-2x ML potential for MD simulations of soft matter systems. Simultaneously, they provide insights for future improvements of current ML potentials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Machine-Learned Linear Structural Dynamics

The tension between accuracy and computational cost is a common thread throughout computational simulation. One such example arises in the modeling of mechanical joints. Joints are typically confined to a physically small domain and yet are computationally expensive to model with a high-resolution finite element representation. A common approach is to substitute reduced-order models that can capture important aspects of the joint response and enable the use of more computationally efficient techniques overall. Unfortunately, such reduced-order models are often difficult to use, error prone, and have a narrow range of application. In contrast, we propose a new type of reduced-order model, leveraging machine learning, that would be both user-friendly and extensible to a wide range of applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Prediction of Dielectric Constant in Series of Polymers by Quantitative Structure-Property Relationship (QSPR)

This work is devoted to the investigation of dielectric permittivity which is influenced by electronic, ionic, and dipolar polarization mechanisms, contributing to the material’s capacity to store electrical energy. In this study, an extended dataset of 86 polymers was analyzed, and two quantitative structure–property relationship (QSPR) models were developed to predict dielectric permittivity. From an initial set of 1273 descriptors, the most relevant ones were selected using a genetic algorithm, and machine learning models were built using the Gradient Boosting Regressor (GBR). In contrast to Multiple Linear Regression (MLR)- and Partial Least Squares (PLS)-based models, the gradient boosting models excel in handling nonlinear relationships and multicollinearity, iteratively optimizing decision trees to improve accuracy without overfitting. The developed GBR models showed high R2 coefficients of 0.938 and 0.822, for the training and test sets, respectively. An Accumulated Local Effect (ALE) technique was applied to assess the relationship between the selected descriptors—eight for the GB_A model and six for the GB_B model, and their impact on target property. ALE analysis revealed that descriptors such as TDB09m had a strong positive effect on permittivity, while MLOGP2 showed a negative effect. These results highlight the effectiveness of the GBR approach in predicting the dielectric properties of polymers, offering improved accuracy and interpretability.

Ascencio-Medina, Estefania↗
NASA NTRS2016

A Quantum-Assisted Algorithm for Sampling Applications in Machine Learning

An increase in the efficiency of sampling from Boltzmann distributions would have a significant impact in deep learning and other machine learning applications. Recently, quantum annealers have been proposed as a potential candidate to speed up this task, but several limitations still bar these state-of-the-art technologies from being used effectively. One of the main limitations is that, while the device may indeed sample from a Boltzmann-like distribution, quantum dynamical arguments suggests it will do so with an instance-dependent effective temperature, different from the physical temperature of the device. Unless this unknown temperature can be unveiled, it might not be possible to effectively use a quantum annealer for Boltzmann sampling. In this talk, we present a strategy to overcome this challenge with a simple effective-temperature estimation algorithm. We provide a systematic study assessing the impact of the effective temperatures in the learning of a kind of restricted Boltzmann machine embedded on quantum hardware, which can serve as a building block for deep learning architectures. We also provide a comparison to k-step contrastive divergence (CD-k) with k up to 100. Although assuming a suitable fixed effective temperature also allows to outperform one step contrastive divergence (CD-1), only when using an instance-dependent effective temperature we find a performance close to that of CD-100 for the case studied here. We discuss generalizations of the algorithm to other more expressive generative models, beyond restricted Boltzmann machines.

Perdomo-Ortiz, Alejandro↗
NASA NTRS1998

Effects of sleep loss, time of day, and extended mental work on implicit and explicit learning of sequences

Tacit knowledge is part of many professional skills and can be studied experimentally with implicit-learning paradigms. The authors explored the effects of 2 different stressors, loss of sleep and mental fatigue, on implicit learning in a serial-response time (RT) task. In the 1st experiment, 1 night of sleep deprivation was shown to impair implicit but not explicit sequence learning. In the 2nd experiment, no impairment of both types of sequence learning was found after 1.5 hr of mental work. Serial-RT performance, in contrast, suffered from both stressors. These findings suggest that sleep deprivation induces specific risks for automatic, skill-based behavior that are not present in consciously controlled performance.

Learning↗
NASA NTRSDate not supplied

Advancements in Blowing Dust Detection at Night via Machine Learning

This presentation introduces operational users to a machine-learning based Dust Probability product developed by the NASA SPoRT program for the application of detecting and monitoring blowing dust plumes at night. Advances in earth observing satellites has improved monitoring and detection of dust both day and night through derived imagery such as the Dust RGB. However, limitations of the RGB at night result in less contrast between dust and land surface features, as seen by the user. A Machine Learning (ML) model has been developed and applied to GOES-16 ABI to overcome this limitation and improve nighttime dust detection. The ML capability is a subset of Artificial Intelligence methods. In this case the Dust ML model was developed using a simple Random Forest (RF) model, typically used to solve classification challenges (or to provide regression type output). The goal was to leverage the strengths of the RF model to learn how to identify blowing dust, and hence, overcome the limitation of a user trying to detect blowing dust within the satellite imagery by eye alone. A brief description of the ML model development will be provided. However, the focus of the presentation will be on the initial user feedback from the assessment of this tool for the 2022 blowing dust events of March through April. During this time several users across the U.S. Southwest collaborated to apply this Dust ML product at night as a complement to the existing Dust RGB in order to determine if it provided greater operational efficiency and value.

Machine Learning↗
DOE OSTI2026

Three-dimensional high-content imaging of unstained soft tissue with subcellular resolution using a laboratory-based X-ray microscope

With increasing interest in studying biological systems across spatial scales—from centimeters down to nanometers—histology continues to be the gold standard for tissue imaging at cellular resolution, providing an essential bridge between macroscopic and nanoscopic analysis. However, its inherently destructive and two-dimensional nature limits its ability to capture the full three-dimensional complexity of tissue architecture. Here, we show that phase-contrast X-ray microscopy can enable three-dimensional virtual histology with subcellular resolution. This technique provides direct quantification of electron density without restrictive assumptions, allowing for direct characterization of cellular nuclei in a standard laboratory setting. By combining high spatial resolution and soft tissue contrast, with automated segmentation of cell nuclei, we demonstrated virtual Hematoxylin and Eosin (H&E) staining using machine learning-based style transfer, yielding volumetric datasets compatible with existing histopathological analysis tools. Furthermore, by integrating electron density and the sensitivity to nanometric features of the dark field contrast channel, we achieve stain-free, high-content imaging capable of distinguishing nuclei and extracellular matrix.

3D virtual histology↗
NASA NTRS2017

Lessons Learned from Applying Design Thinking in a NASA Rapid Design Study in Aeronautics

In late 2015, NASA's Aeronautics Research Mission Directorate (ARMD) funded an experiment in rapid design and rapid teaming to explore new approaches to solving challenging design problems in aeronautics in an effort to cultivate and foster innovation. This report summarizes several lessons learned from the rapid design portion of the study. This effort entailed learning and applying design thinking, a human-centered design approach, to complete the conceptual design for an open-ended design challenge within six months. The design challenge focused on creating a capability to advance experimental testing of autonomous aeronautics systems, an area of great interest to NASA, the US government as a whole, and an entire ecosystem of users and developers around the globe. A team of nine civil servant researchers from three of NASA's aeronautics field centers with backgrounds in several disciplines was assembled and rapidly trained in design thinking under the guidance of the innovation and design firm IDEO. The design thinking process, while used extensively outside the aerospace industry, is less common and even counter to many practices within the aerospace industry. In this report, several contrasts between common aerospace research and development practices and design thinking are discussed, drawing upon the lessons learned from the NASA rapid design study. The lessons discussed included working towards a design solution without a set of detailed design requirements, which may not be practical or even feasible for management to ascertain for complex, challenging problems. This approach allowed for the possibility of redesigning the original problem statement to better meet the needs of the users. Another lesson learned was to approach problems holistically from the perspective of the needs of individuals that may be affected by advances in topic area instead of purely from a technological feasibility viewpoint. The interdisciplinary nature of the design team also provided valuable experience by allowing team members from different technological backgrounds to work side-by-side instead of dividing into smaller teams, as is frequently done in traditional multidisciplinary design. The team also learned how to work with qualitative data obtained primarily through the 70-plus interviews that were conducted over the course of this project, which was a sharp contrast to using quantitative data with regards to identifying, capturing, analyzing, storing, and recalling the data. When identifying potential interviewees who may have useful contributions to the design subject area, the team found great value in talking to non-traditional users and potential beneficiaries of autonomous aeronautics systems whose impact on the aeronautics autonomy ecosystem is growing swiftly. Finally, the team benefitted from using "sacrificial prototyping," which is a method of rapidly prototyping draft concepts and ideas with the intent of enabling potential users to provide significant feedback early in the design process. This contrasts the more common approach of using expensive prototypes that focus on demonstrating technical feasibility. The unique design approach and lessons learned by the team throughout this process culminated in a final design concept that was quite different than what the team originally assumed would be the design concept initially. A summary of the more usercentered final design concept is also provided.

McGowan, Anna-Maria↗
NASA NTRS2016

Laboratory Testing and Performance Verification of the CHARIS Integral Field Spectrograph

The Coronagraphic High Angular Resolution Imaging Spectrograph (CHARIS) is an integral field spectrograph (IFS) that has been built for the Subaru telescope. CHARIS has two imaging modes; the high-resolution mode is R82, R69, and R82 in J, H, and K bands respectively while the low-resolution discovery mode uses a second low-resolution prism with R19 spanning 1.15-2.37 microns (J+H+K bands). The discovery mode is meant to augment the low inner working angle of the Subaru Coronagraphic Extreme Adaptive Optics (SCExAO) adaptive optics system, which feeds CHARIS a coronagraphic image. The goal is to detect and characterize brown dwarfs and hot Jovian planets down to contrasts five orders of magnitude dimmer than their parent star at an inner working angle as low as 80 milliarcseconds. CHARIS constrains spectral crosstalk through several key aspects of the optical design. Additionally, the repeatability of alignment of certain optical components is critical to the calibrations required for the data pipeline. Specifically the relative alignment of the lens let array, prism, and detector must be highly stable and repeatable between imaging modes. We report on the measured repeatability and stability of these mechanisms, measurements of spectral crosstalk in the instrument, and the propagation of these errors through the data pipeline. Another key design feature of CHARIS is the prism, which pairs Barium Fluoride with Ohara L-BBH2 high index glass. The dispersion of the prism is significantly more uniform than other glass choices, and the CHARIS prisms represent the first NIR astronomical instrument that uses L-BBH2as the high index material. This material choice was key to the utility of the discovery mode, so significant efforts were put into cryogenic characterization of the material. The final performance of the prism assemblies in their operating environment is described in detail. The spectrograph is going through final alignment, cryogenic cycling, and is being delivered to the Subaru telescope in April 2016. This paper is a report on the laboratory performance of the spectrograph, and its current status in the commissioning process so that observers will better understand the instrument capabilities. We will also discuss the lessons learned during the testing process and their impact on future high-contrast imaging spectrographs for wavefront control.

Coronagraphic High Angular Resolution Imaging Spec↗
DOE OSTI2021

Deep learning-based segmentation of lithium-ion battery microstructures enhanced by artificially generated electrodes

Accurate 3D representations of lithium-ion battery electrodes, in which the active particles, binder and pore phases are distinguished and labeled, can assist in understanding and ultimately improving battery performance. Here, we demonstrate a methodology for using deep-learning tools to achieve reliable segmentations of volumetric images of electrodes on which standard segmentation approaches fail due to insufficient contrast. We implement the 3D U-Net architecture for segmentation, and, to overcome the limitations of training data obtained experimentally through imaging, we show how synthetic learning data, consisting of realistic artificial electrode structures and their tomographic reconstructions, can be generated and used to enhance network performance. We apply our method to segment x-ray tomographic microscopy images of graphite-silicon composite electrodes and show it is accurate across standard metrics. We then apply it to obtain a statistically meaningful analysis of the microstructural evolution of the carbon-black and binder domain during battery operation.

25 ENERGY STORAGE↗
NASA NTRS2012

Hybrid Collaborative Learning for Classification and Clustering in Sensor Networks

Traditionally, nodes in a sensor network simply collect data and then pass it on to a centralized node that archives, distributes, and possibly analyzes the data. However, analysis at the individual nodes could enable faster detection of anomalies or other interesting events as well as faster responses, such as sending out alerts or increasing the data collection rate. There is an additional opportunity for increased performance if learners at individual nodes can communicate with their neighbors. In previous work, methods were developed by which classification algorithms deployed at sensor nodes can communicate information about event labels to each other, building on prior work with co-training, self-training, and active learning. The idea of collaborative learning was extended to function for clustering algorithms as well, similar to ideas from penta-training and consensus clustering. However, collaboration between these learner types had not been explored. A new protocol was developed by which classifiers and clusterers can share key information about their observations and conclusions as they learn. This is an active collaboration in which learners of either type can query their neighbors for information that they then use to re-train or re-learn the concept they are studying. The protocol also supports broadcasts from the classifiers and clusterers to the rest of the network to announce new discoveries. Classifiers observe an event and assign it a label (type). Clusterers instead group observations into clusters without assigning them a label, and they collaborate in terms of pairwise constraints between two events [same-cluster (mustlink) or different-cluster (cannot-link)]. Fundamentally, these two learner types speak different languages. To bridge this gap, the new communication protocol provides four types of exchanges: hybrid queries for information, hybrid "broadcasts" of learned information, each specified for classifiers-to-clusterers, and clusterers-to-classifiers. The new capability has the potential to greatly expand the in situ analysis abilities of sensor networks. Classifiers seeking to categorize incoming data into different types of events can operate in tandem with clusterers that are sensitive to the occurrence of new kinds of events not known to the classifiers. In contrast to current approaches that treat these operations as independent components, a hybrid collaborative learning system can enable them to learn from each other.

Wagstaff, Kiri L.↗
DOE OSTI2024

Reinforcement learning pulses for transmon qubit entangling gates

The utility of a quantum computer is highly dependent on the ability to reliably perform accurate quantum logic operations. For finding optimal control solutions, it is of particular interest to explore model-free approaches, since their quality is not constrained by the limited accuracy of theoretical models for the quantum processor—in contrast to many established gate implementation strategies. In this work, we utilize a continuous control reinforcement learning algorithm to design entangling two-qubit gates for superconducting qubits; specifically, our agent constructs cross-resonance and CNOT gates without any prior information about the physical system. Using a simulated environment of fixed-frequency fixed-coupling transmon qubits, we demonstrate the capability to generate novel pulse sequences that outperform the standard cross-resonance gates in both fidelity and gate duration, while maintaining a comparable susceptibility to stochastic unitary noise. We further showcase an augmentation in training and input information that allows our agent to adapt its pulse design abilities to drifting hardware characteristics, importantly, with little to no additional optimization. Our results exhibit clearly the advantages of unbiased adaptive-feedback learning-based optimization methods for transmon gate design.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗