SEARCH · Search NASA

Results for “learnability”

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.

SourceResearch connectionFrom yearThrough year

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

60 records · Page 4

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

QuantifyML: How Good is My Machine Learning Model?

We present QuantifyML, which applies model counting to assess the learn ability, safety, and robustness of machine learning models. Typically, the efficacy of machine learning models is determined by computing their accuracy statistically on test datasets. However, this may be misleading, if the test data is not representative of the problem that is being studied. With QuantifyML we aim to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into aC program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise countsw.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, ex-pressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the safety and robustness of trained models.

Deep Neural Networks↗

NASA NTRSDate not supplied

What is the Role of Usability and Trust in Autonomy?

Usability encompasses learnability, efficiency, memorability, effectiveness, and satisfaction. NASA’s standards for usability acceptance criteria focus on interfaces that help operators achieve their tasks efficiently, effectively, and with satisfaction. However, discussions on usability, especially regarding future highly automated and autonomous systems, rarely include trust. As NASA plans for long-duration exploration missions, it envisions astronauts operating more independently from Mission Control on Earth. This independence will drive the development of these highly automated and autonomous systems that astronauts will use daily. To prepare for this future, our team has developed a scheduling and execution software tool that facilitates self-scheduling, allowing astronauts to independently manage their own schedule without Mission Control’s involvement. Over many years, we have developed, matured, and evaluated our software tool in extreme environments, prioritizing user-centered design and high usability. These evaluations have included multiple campaigns in NASA analogs, including NEEMO, BASALT, and HERA, as well as technology demonstrations onboard the International Space Station. Our recent research on software interfaces for future astronaut autonomy revealed a strong correlation between usability and trust measures. In a controlled lab experiment, we asked novice users to perform a complex scheduling task, during which the software immediately validated the schedule’s constraints and checked for violations. We collected usability (User Experience Questionnaire, UEQ) and trust (Trust in Automated Systems scale, TAS) measures; significant, strong, and moderate correlations emerged between several of the UEQ metrics and TAS. These results support the argument for investing in usability early to enable and sustain trust in highly automated and autonomous systems.

usability↗

DOE OSTI2022

Do graph neural networks learn traditional jet substructure?

At the CERN LHC, the task of jet tagging, whose goal is to infer the origin of a jet given a set of final-state particles, is dominated by machine learning methods. Graph neural networks have been used to address this task by treating jets as point clouds with underlying, learnable, edge connections between the particles inside. We explore the decision-making process for one such state-of-the-art network, ParticleNet, by looking for relevant edge connections identified using the layerwise-relevance propagation technique. As the model is trained, we observe changes in the distribution of relevant edges connecting different intermediate clusters of particles, known as subjets. The resulting distribution of subjet connections is different for signal jets originating from top quarks, whose subjets typically correspond to its three decay products, and background jets originating from lighter quarks and gluons. This behavior indicates that the model is using traditional jet substructure observables, such as the number of prongs -- energetic particle clusters -- within a jet, when identifying jets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2026

Neural Scaling Laws for Jet Generation

Recently observed empirical scaling laws describe the performance of foundation-type models as three independent key quantities -- dataset size, compute, and model parameters -- are modified. Extracting these scaling laws informs the training of large complex models for which the tuning of hyperparameters in traditional ways is not feasible. This work for the first time explores if scaling laws can also be observed for the task of particle jet generation -- both relevant as a pre-training objective for foundation models and as in-situ simulation by itself. We indeed replicate the key logarithmic scaling law behavior for model-size scaling. Beyond studying the next token prediction validation loss of the generative model, we also study the sliced Wasserstein distance of five physical quantities that are not immediately available to the model during training. Our study shows that this quantity is monotonically related to the next token prediction validation loss, meaning that this loss is indeed a good proxy for the physics performance. For the scaling with dataset size and compute, we observe substantially weaker scaling behavior of both the loss and the sliced Wasserstein distance. We analyze this behavior by introducing the concept of a learnable window, and argue that autoregressive next token prediction on jet constituents exhibits comparatively rapid saturation relative to language-model studies. We discuss possible origins of this behavior, including the stochastic nature of QCD radiation and differences between generative and supervised learning tasks in collider physics.

Amram, Oz [Fermilab]↗

DOE OSTI2026

Universal monitored dynamics in multimode bosonic systems

We propose a route to study monitored many-body dynamics in multimode bosonic systems using circuit quantum electrodynamics. In this experimental setting, we construct several bosonic models comprising brickwork circuits built from beam-splitter gates, local parity measurements, and optional on-site Hubbard interactions, and diagnose their monitored dynamics via ancilla purification and a learnability-based probe. Under parity measurements, generic gate sets exhibit behavior that is largely consistent with a conventional measurement-induced phase transition, while a special class of beam-splitter circuits shows an apparent critical-like high-measurement regime in which purification times scale linearly with system size. We show that for realistic noise, gate, and measurement rates, these signatures are observable with near-term circuit QED hardware.

Patel, Shivam [Rutgers U., Piscataway]↗

DOE OSTI2020

Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness

We report the accuracy of deep learning, i.e., deep neural networks, can be characterized by dividing the total error into three main types: approximation error, optimization error, and generalization error. Whereas there are some satisfactory answers to the problems of approximation and optimization, much less is known about the theory of generalization. Most existing theoretical works for generalization fail to explain the performance of neural networks in practice. To derive a meaningful bound, we study the generalization error of neural networks for classification problems in terms of data distribution and neural network smoothness. We introduce the cover complexity (CC) to measure the difficulty of learning a data set and the inverse of the modulus of continuity to quantify neural network smoothness. A quantitative bound for expected accuracy/error is derived by considering both the CC and neural network smoothness. Although most of the analysis is general and not specific to neural networks, we validate our theoretical assumptions and results numerically for neural networks by several data sets of images. The numerical results confirm that the expected error of trained networks scaled with the square root of the number of classes has a linear relationship with respect to the CC. We also observe a clear consistency between test loss and neural network smoothness during the training process. In addition, we demonstrate empirically that the neural network smoothness decreases when the network size increases whereas the smoothness is insensitive to training dataset size.

97 MATHEMATICS AND COMPUTING↗