SEARCH · Search NASA

Results for “algorithmic differentiation”

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.

At least 775 records · Page 43

All sources NASA NTRS DOE OSTI

DOE OSTI2011

ELASTI

The mathematical underpinning of algorithm ELASTI is the so-called velocity-stress system of coupled partial differential equations governing linear (i.e., infinitesimal deformation) seismic wave propagation within a three-dimensional isotropic elastic body The medium is characterized by the three parameters: compressional (P) wave speed, shear (S) wave speed, and mass density, all of which may vary in the three spatial dimensions. The nine dependent variables (three particle velocity vector components and six stress tensor components) are stored within the algorithm on staggered spatial and temporal grids. The 3D spatial grid is rectangular, and grid intervals are uniform in each coordinate direction. Numerical solution methodology consists of explicit, time-domain, finite-differencing. Discrete finite-difference (FD) operators approximating partial derivatives possess 2nd-order accuracy in time and 4th-order accuracy in space. FD formulae for updating the wavefield variables are appropriately non-dimensionalized and normalized so that single-precision arithmetic calculations yield 1105824/01 adequate accuracy. This software will be used to generate seismic responses for typical geological/geophysical models of interest in the petroleum, mining, geotechnical, geothermal, hydrological, environmental assessment, and underground storage industries. Additionally, US government agencies (including the military) involved in monitoring of explosions or remote surveillance of underground facilities.

Aldridge, David F↗

DOE OSTI2022

Differential methods for assessing sensitivity in biological models

Differential sensitivity analysis is indispensable in fitting parameters, understanding uncertainty, and forecasting the results of both thought and lab experiments. Although there are many methods currently available for performing differential sensitivity analysis of biological models, it can be difficult to determine which method is best suited for a particular model. In this paper, we explain a variety of differential sensitivity methods and assess their value in some typical biological models. First, we explain the mathematical basis for three numerical methods: adjoint sensitivity analysis, complex perturbation sensitivity analysis, and forward mode sensitivity analysis. We then carry out four instructive case studies. (a) The CARRGO model for tumor-immune interaction highlights the additional information that differential sensitivity analysis provides beyond traditional naive sensitivity methods, (b) the deterministic SIR model demonstrates the value of using second-order sensitivity in refining model predictions, (c) the stochastic SIR model shows how differential sensitivity can be attacked in stochastic modeling, and (d) a discrete birth-death-migration model illustrates how the complex perturbation method of differential sensitivity can be generalized to a broader range of biological models. Finally, we compare the speed, accuracy, and ease of use of these methods. We find that forward mode automatic differentiation has the quickest computational time, while the complex perturbation method is the simplest to implement and the most generalizable.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2015

TU-AB-BRA-12: Impact of Image Registration Algorithms On the Prediction of Pathological Response with Radiomic Textures

Purpose: Tumor regions-of-interest (ROI) can be propagated from the pre-onto the post-treatment PET/CT images using image registration of their CT counterparts, providing an automatic way to compute texture features on longitudinal scans. This exploratory study assessed the impact of image registration algorithms on textures to predict pathological response. Methods: Forty-six esophageal cancer patients (1 tumor/patient) underwent PET/CT scans before and after chemoradiotherapy. Patients were classified into responders and non-responders after the surgery. Physician-defined tumor ROIs on pre-treatment PET were propagated onto the post-treatment PET using rigid and ten deformable registration algorithms. One co-occurrence, two run-length and size zone matrix textures were computed within all ROIs. The relative difference of each texture at different treatment time-points was used to predict the pathologic responders. Their predictive value was assessed using the area under the receiver-operating-characteristic curve (AUC). Propagated ROIs and texture quantification resulting from different algorithms were compared using overlap volume (OV) and coefficient of variation (CoV), respectively. Results: Tumor volumes were better captured by ROIs propagated by deformable rather than the rigid registration. The OV between rigidly and deformably propagated ROIs were 69%. The deformably propagated ROIs were found to be similar (OV∼80%) except for fast-demons (OV∼60%). Rigidly propagated ROIs with run-length matrix textures failed to significantly differentiate between responders and non-responders (AUC=0.65, p=0.07), while the differentiation was significant with other textures (AUC=0.69–0.72, p<0.03). Among the deformable algorithms, fast-demons was the least predictive (AUC=0.68–0.71, p<0.04). ROIs propagated by all other deformable algorithms with any texture significantly predicted pathologic responders (AUC=0.71–0.78, p<0.01) despite substantial variation in texture quantification (CoV>70%). Conclusion: Propagated ROIs using deformable registration for all textures can lead to accurate prediction of pathologic response, potentially expediting the temporal texture analysis process. However, rigid and fast-demons deformable algorithms are not recommended due to their inferior performance compared to other algorithms. The project was supported in part by a Kaye Scholar Award.

60 APPLIED LIFE SCIENCES↗

NASA NTRS2013

Fuzzy Reasoning to More Accurately Determine Void Areas on Optical Micrographs of Composite Structures

Accomplishing the best-performing composite matrix (resin) requires that not only the processing method but also the cure cycle generate low-void-content structures. If voids are present, the performance of the composite matrix will be significantly reduced. This is usually noticed by significant reductions in matrix-dominated properties, such as compression and shear strength. Voids in composite materials are areas that are absent of the composite components: matrix and fibers. The characteristics of the voids and their accurate estimation are critical to determine for high performance composite structures. One widely used method of performing void analysis on a composite structure sample is acquiring optical micrographs or Scanning Electron Microscope (SEM) images of lateral sides of the sample and retrieving the void areas within the micrographs/images using an image analysis technique. Segmentation for the retrieval and subsequent computation of void areas within the micrographs/images is challenging as the gray-scaled values of the void areas are close to the gray-scaled values of the matrix leading to the need of manually performing the segmentation based on the histogram of the micrographs/images to retrieve the void areas. The use of an algorithm developed by NASA and based on Fuzzy Reasoning (FR) proved to overcome the difficulty of suitably differentiate void and matrix image areas with similar gray-scaled values leading not only to a more accurate estimation of void areas on composite matrix micrographs but also to a faster void analysis process as the algorithm is fully autonomous.

Dominquez, Jesus A.↗

DOE OSTI2016

Finite element formulation of fluctuating hydrodynamics for fluids filled with rigid particles using boundary fitted meshes

In this paper, we present a finite element implementation of fluctuating hydrodynamics with a moving boundary fitted mesh for treating the suspended particles. The thermal fluctuations are incorporated into the continuum equations using the Landau and Lifshitz approach [1]. The proposed implementation fulfills the fluctuation–dissipation theorem exactly at the discrete level. Since we restrict the equations to the creeping flow case, this takes the form of a relation between the diffusion coefficient matrix and friction matrix both at the particle and nodal level of the finite elements. Brownian motion of arbitrarily shaped particles in complex confinements can be considered within the present formulation. A multi-step time integration scheme is developed to correctly capture the drift term required in the stochastic differential equation (SDE) describing the evolution of the positions of the particles. The proposed approach is validated by simulating the Brownian motion of a sphere between two parallel plates and the motion of a spherical particle in a cylindrical cavity. The time integration algorithm and the fluctuating hydrodynamics implementation are then applied to study the diffusion and the equilibrium probability distribution of a confined circle under an external harmonic potential.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2014

TH-E-BRE-05: Analysis of Dosimetric Characteristics in Two Leaf Motion Calculator Algorithms for Sliding Window IMRT

Purpose: The Smart leaf motion calculator (SLMC) in Eclipse treatment planning system is an advanced fluence delivery modeling algorithm as it takes into account fine MLC features including inter-leaf leakage, rounded leaf tips, non-uniform leaf thickness, and the spindle cavity etc. In this study, SLMC and traditional Varian LMC (VLMC) algorithms were investigated, for the first time, in dosimetric characteristics and delivery accuracy of sliding window (SW) IMRT. Methods: The SW IMRT plans of 51 cancer cases were included to evaluate dosimetric characteristics and dose delivery accuracy from leaf motion calculated by SLMC and VLMC, respectively. All plans were delivered using a Varian TrueBeam Linac. The DVH and MUs of the plans were analyzed. Three patient specific QA tools - independent dose calculation software IMSure, Delta4 phantom, and EPID portal dosimetry were also used to measure the delivered dose distribution. Results: Significant differences in the MUs were observed between the two LMCs (p≤0.001).Gamma analysis shows an excellent agreement between the planned dose distribution calculated by both LMC algorithms and delivered dose distribution measured by three QA tools in all plans at 3%/3 mm, leading to a mean pass rate exceeding 97%. The mean fraction of pixels with gamma < 1 of SLMC is slightly lower than that of VLMC in the IMSure and Delta4 results, but higher in portal dosimetry (the highest spatial resolution), especially in complex cases such as nasopharynx. Conclusion: The study suggests that the two LMCs generates the similar target coverage and sparing patterns of critical structures. However, SLMC is modestly more accurate than VLMC in modeling advanced MLC features, which may lead to a more accurate dose delivery in SW IMRT. Current clinical QA tools might not be specific enough to differentiate the dosimetric discrepancies at the millimeter level calculated by these two LMC algorithms. NIH/NIGMS grant U54 GM104944, Lincy Endowed Assistant Professorship.

60 APPLIED LIFE SCIENCES↗

NASA NTRS1992

Spurious Solutions Of Nonlinear Differential Equations

Report utilizes nonlinear-dynamics approach to investigate possible sources of errors and slow convergence and non-convergence of steady-state numerical solutions when using time-dependent approach for problems containing nonlinear source terms. Emphasizes implications for development of algorithms in CFD and computational sciences in general. Main fundamental conclusion of study is that qualitative features of nonlinear differential equations cannot be adequately represented by finite-difference method and vice versa.

Yee, H. C.↗

DOE OSTI2017

Evaluation of a Machine-Learning Algorithm for Treatment Planning in Prostate Low-Dose-Rate Brachytherapy

Purpose: This work presents the application of a machine learning (ML) algorithm to automatically generate high-quality, prostate low-dose-rate (LDR) brachytherapy treatment plans. The ML algorithm can mimic characteristics of preoperative treatment plans deemed clinically acceptable by brachytherapists. The planning efficiency, dosimetry, and quality (as assessed by experts) of preoperative plans generated with an ML planning approach was retrospectively evaluated in this study. Methods and Materials: Preimplantation and postimplantation treatment plans were extracted from 100 high-quality LDR treatments and stored within a training database. The ML training algorithm matches similar features from a new LDR case to those within the training database to rapidly obtain an initial seed distribution; plans were then further fine-tuned using stochastic optimization. Preimplantation treatment plans generated by the ML algorithm were compared with brachytherapist (BT) treatment plans in terms of planning time (Wilcoxon rank sum, α = 0.05) and dosimetry (1-way analysis of variance, α = 0.05). Qualitative preimplantation plan quality was evaluated by expert LDR radiation oncologists using a Likert scale questionnaire. Results: The average planning time for the ML approach was 0.84 ± 0.57 minutes, compared with 17.88 ± 8.76 minutes for the expert planner (P=.020). Preimplantation plans were dosimetrically equivalent to the BT plans; the average prostate V150% was 4% lower for ML plans (P=.002), although the difference was not clinically significant. Respondents ranked the ML-generated plans as equivalent to expert BT treatment plans in terms of target coverage, normal tissue avoidance, implant confidence, and the need for plan modifications. Respondents had difficulty differentiating between plans generated by a human or those generated by the ML algorithm. Conclusions: Prostate LDR preimplantation treatment plans that have equivalent quality to plans created by brachytherapists can be rapidly generated using ML. The adoption of ML in the brachytherapy workflow is expected to improve LDR treatment plan uniformity while reducing planning time and resources.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2020

Adaptive Activation Functions Accelerate Convergence in Deep and Physics-informed Neural Networks

We employ adaptive activation functions for regression in deep and physics-informed neural networks (PINNs) to approximate smooth and discontinuous functions as well as solutions of linear and nonlinear partial differential equations. In particular, we solve the nonlinear Klein-Gordon equation, which has smooth solutions, the nonlinear Burgers equation, which can admit high gradient solutions, and the Helmholtz equation. We introduce a scalable hyper-parameter in the activation function, which can be optimized to achieve best performance of the network as it changes dynamically the topology of the loss function involved in the optimization process. The adaptive activation function has better learning capabilities than the traditional one (fixed activation) as it improves greatly the convergence rate, especially at early training, as well as the solution accuracy. To better understand the learning process, we plot the neural network solution in the frequency domain to examine how the network captures successively different frequency bands present in the solution. We consider both forward problems, where the approximate solutions are obtained, as well as inverse problems, where parameters involved in the governing equation are identified. Our simulation results show that the proposed method is a very simple and effective approach to increase the efficiency, robustness and accuracy of the neural network approximation of nonlinear functions as well as solutions of partial differential equations, especially for forward problems. We theoretically prove that in the proposed method, gradient descent algorithms are not attracted to suboptimal critical points or local minima.

machine leaning, Bad minima, Inverse problems, Phy↗

DOE OSTI2023

A greedy Galerkin method to efficiently select sensors for linear dynamical systems

A key challenge in inverse problems is the selection of sensors to gather the most effective data. In this paper, we consider the problem of inferring the initial condition to a linear dynamical system and develop an efficient control-theoretical approach for greedily selecting sensors. Our method employs a Galerkin projection to reduce the size of the inverse problem, resulting in a computationally efficient algorithm for sensor selection. As a byproduct of our algorithm, we obtain a preconditioner for the inverse problem that enables the rapid recovery of the initial condition. Here, we analyze the theoretical performance of our greedy sensor selection algorithm as well as the performance of the associated preconditioner. Finally, we verify our theoretical results on various inverse problems involving partial differential equations.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Geometric Interpretation of the Cluster Location Problem Part I: Theory

We present a new framing of the seismic location problem using principles drawn from differential geometry. Our interpretation relies upon the common assumption that travel times observed across a network are continuous, differentiable functions of source location. In consequence, travel‐time functions constitute a differentiable map between the source region and a Riemannian manifold. The manifold is said to be the image of the source region embedded in a generally high‐dimension travel‐time vector space. A cluster of events in the source region has an image of discrete points on the manifold, that, except in the simplest cases, cannot be viewed directly. However, it is possible to project the image of a cluster into a tangent space of the manifold for direct visualization. The projection operator can be computed directly from the data without a velocity model, but produces a distorted rendering of the cluster geometry. With a model we can predict the distortions and correct them to estimate cluster geometry. We develop these points with the simplest possible example, one for which direct visualization of the manifold is possible, using the example as an introduction to the relevant concepts from differential geometry in a familiar setting. The tangent space, a local linearization of the manifold, plays a key role. We develop a metric to estimate the limits of linearization, that is, to determine when the curvature of the manifold invalidates the linear assumption. We also examine the interplay of model error, inadequate network geometry, and pick error. We then generalize our results from the simple case to the general case of 3D source regions observed by general networks. Although we do suggest a new “project and correct” method for location, we do not develop it into a practical algorithm. In conclusion, our intention rather is to highlight new analytical methods grounded in differential geometry.

East Pacific Ocean Islands↗

DOE OSTI2015

MO-F-CAMPUS-J-05: Toward MRI-Only Radiotherapy: Novel Tissue Segmentation and Pseudo-CT Generation Techniques Based On T1 MRI Sequences

Purpose: To develop and validate a 4 class tissue segmentation approach (air cavities, background, bone and soft-tissue) on T1 -weighted brain MRI and to create a pseudo-CT for MRI-only radiation therapy verification. Methods: Contrast-enhanced T1-weighted fast-spin-echo sequences (TR = 756ms, TE= 7.152ms), acquired on a 1.5T GE MRI-Simulator, are used.MRIs are firstly pre-processed to correct for non uniformity using the non parametric, non uniformity intensity normalization algorithm. Subsequently, a logarithmic inverse scaling log(1/image) is applied, prior to segmentation, to better differentiate bone and air from soft-tissues. Finally, the following method is enrolled to classify intensities into air cavities, background, bone and soft-tissue:Thresholded region growing with seed points in image corners is applied to get a mask of Air+Bone+Background. The background is, afterward, separated by the scan-line filling algorithm. The air mask is extracted by morphological opening followed by a post-processing based on knowledge about air regions geometry. The remaining rough bone pre-segmentation is refined by applying 3D geodesic active contours; bone segmentation evolves by the sum of internal forces from contour geometry and external force derived from image gradient magnitude.Pseudo-CT is obtained by assigning −1000HU to air and background voxels, performing linear mapping of soft-tissue MR intensities in [-400HU, 200HU] and inverse linear mapping of bone MR intensities in [200HU, 1000HU]. Results: Three brain patients having registered MRI and CT are used for validation. CT intensities classification into 4 classes is performed by thresholding. Dice and misclassification errors are quantified. Correct classifications for soft-tissue, bone, and air are respectively 89.67%, 77.8%, and 64.5%. Dice indices are acceptable for bone (0.74) and soft-tissue (0.91) but low for air regions (0.48). Pseudo-CT produces DRRs with acceptable clinical visual agreement to CT-based DRR. Conclusion: The proposed approach makes it possible to use T1-weighted MRI to generate accurate pseudo-CT from 4-class segmentation.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2019

An Evolve-Filter-Relax Stabilized Reduced Order Stochastic Collocation Method for the Time-Dependent Navier--Stokes Equations

In this paper, we propose a filter-based stabilization of reduced order models (ROMs) for uncertainty quantification (UQ) of the time-dependent Navier--Stokes equations in convection-dominated regimes. Here we propose a novel high-order ROM differential filter and use it in conjunction with an evolve-filter-relax (EFR) algorithm to attenuate the numerical oscillations of standard ROMs. We also examine how stochastic collocation methods can be combined with the EFR algorithm for efficient UQ of fluid flows. We test the new framework in the numerical simulation of a two-dimensional flow past a circular cylinder with a random viscosity that yields a random Reynolds number with mean Re = 100.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Tusas: A fully implicit parallel approach for coupled phase-field equations

In this study, we develop a fully-coupled, fully-implicit approach for phase-field modeling of solidification in metals and alloys. Predictive simulation of solidification in pure metals and metal alloys remains a significant challenge in the field of materials science, as microstructure formation during the solidification process plays a critical role in the properties and performance of the solid material. Our simulation approach consists of a finite element spatial discretization of the fully-coupled nonlinear system of partial differential equations at the microscale, which is treated implicitly in time with a preconditioned Jacobian-free Newton-Krylov method. The approach is algorithmically scalable as well as efficient due to an effective preconditioning strategy based on algebraic multigrid and block factorization. We implement this approach in the open-source Tusas framework, which is a general, flexible tool developed in C++ for solving coupled systems of nonlinear partial differential equations. The performance of our approach is analyzed in terms of algorithmic scalability and efficiency, while the computational performance of Tusas is presented in terms of parallel scalability and efficiency on emerging heterogeneous architectures. We demonstrate that modern algorithms, discretizations, and computational science, and heterogeneous hardware provide a robust route for predictive phase-field simulation of microstructure evolution during additive manufacturing.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

nPINNs: Nonlocal physics-informed neural networks for a parametrized nonlocal universal Laplacian operator. Algorithms and applications

Physics-informed neural networks (PINNs) are effective in solving inverse problems based on differential and integro-differential equations with sparse, noisy, unstructured, and multifidelity data. PINNs incorporate all available information, including governing equations (reflecting physical laws), initial-boundary conditions, and observations of quantities of interest, into a loss function to be minimized, thus recasting the original problem into an optimization problem. In this paper, we extend PINNs to parameter and function inference for integral equations such as nonlocal Poisson and nonlocal turbulence models, and we refer to them as nonlocal PINNs (nPINNs). The contribution of the paper is three-fold. First, we propose a unified nonlocal Laplace operator, which converges to the classical Laplacian as one of the operator parameters, the nonlocal interaction radius $\delta$ goes to zero, and to the fractional Laplacian as $\delta$ goes to infinity. This universal operator forms a super-set of classical Laplacian and fractional Laplacian operators and, thus, has the potential to fit a broad spectrum of data sets. We also provide theoretical convergence rates with respect to $\delta$ and verify them via numerical experiments. Second, we use nPINNs to estimate the two parameters, $\delta$ and $\alpha$, characterizing the kernel of the unified operator. The strong non-convexity of the loss function yielding multiple (good) local minima reveals the occurrence of the operator mimicking phenomenon, that is, different pairs of estimated parameters could produce multiple solutions of comparable accuracy. Third, we propose another nonlocal operator with spatially variable order $\alpha(y)$, which is more suitable for modeling turbulent Couette flow. Our results show that nPINNs can jointly infer this function as well as $\delta$. More importantly, these parameters exhibit a universal behavior with respect to the Reynolds number, a finding that contributes to our understanding of nonlocal interactions in wall-bounded turbulence.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

nPINNs: nonlocal Physics-Informed Neural Networks for a parametrized nonlocal universal Laplacian operator. Algorithms and Applications

Physics-informed neural networks (PINNs) are effective in solving inverse problems based on differential and integro-differential equations with sparse, noisy, unstructured, and multifidelity data. PINNs incorporate all available information, including governing equations (reflecting physical laws), initial-boundary conditions, and observations of quantities of interest, into a loss function to be minimized, thus recasting the original problem into an optimization problem. In this paper, we extend PINNs to parameter and function inference for integral equations such as nonlocal Poisson and nonlocal turbulence models, and we refer to them as nonlocal PINNs (nPINNs). The contribution of the paper is three-fold. First, we propose a unified nonlocal Laplace operator, which converges to the classical Laplacian as one of the operator parameters, the nonlocal interaction radius δ goes to zero, and to the fractional Laplacian as δ goes to infinity. This universal operator forms a super-set of classical Laplacian and fractional Laplacian operators and, thus, has the potential to fit a broad spectrum of data sets. We provide theoretical convergence rates with respect to δ and verify them via numerical experiments. Second, we use nPINNs to estimate the two parameters, δ and α, characterizing the kernel of the unified operator. The strong non-convexity of the loss function yielding multiple (good) local minima reveals the occurrence of the operator mimicking phenomenon, that is, different pairs of estimated parameters could produce multiple solutions of comparable accuracy. Third, we propose another nonlocal operator with spatially variable order α(γ), which is more suitable for modeling turbulent Couette flow. Our results show that nPINNs can jointly infer this function as well as δ. More importantly, these parameters exhibit a universal behavior with respect to the Reynolds number, a finding that contributes to our understanding of nonlocal interactions in wall-bounded turbulence.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

NASA NTRS1981

Multigrid solvers on parallel computers

Massively parallel computers, as considered in this investigation, are not yet available. However, a large-scale parallel computer cannot usefully be designed before the hypothetical algorithms which will employ it are studied. Most of the studies of parallel partial differential equations (PDE) solvers are based on solution techniques much slower (on sequential machines) than multigrid methods. Multigrid methods are highly parallelizable. Each of their processes can simultaneously be performed at all grid points. The present investigation is concerned with a preliminary exploration of the potential of multigrid, or, more generally, Multi-Level Adaptive Techniques (MLAT) on computers with many processors. Basic processes are considered, taking into account coarse-grid approximation, relaxation, coarse-grid corrections, full multigrid algorithms, nonlinear problems and eigenvalue problems, fine-to-coarse correction, and chains of problems. Details of parallel multigrid processing are also examined.

Brandt, A.↗

DOE OSTI2023

Domain Aware Deep-learning Algorithms Integrated with Scientific-computing Technologies (DADAIST)

This technical report summarized the contribution of the DADAIST project funded by the Data Model Convergence Initiative via the Laboratory Directed Research and Development (LDRD) investments at Pacific Northwest National Laboratory (PNNL). Specifically, we report the development of the NeuroMANCER (Neural Modules with Adaptive Nonlinear Constraints and Efficient Regularizations), a new open-source Scientific Machine Learning library for formulating and solving parametric constrained optimization problems, physics-informed system identification, and parametric optimal control problems. NeuroMANCER is using differentiable programming to combine modern data-driven models and optimization modeling language into a coherent algorithmic and software framework. NeuroMANCER is a Pytorch-based framework and adopts much of its philosophy focused on research and development, rapid prototyping, and streamlined deployment. Strong emphasis is given to extensibility, interoperability with the PyTorch ecosystem, and quick adaptability to custom domain problems. Neuromancer repository contains a comprehensive library of differentiable modules, including custom activation functions, matrix factorizations, deep learning architectures, neural differential equations, differential equation solvers, implicit layers such as iterative solvers, high-level API for symbolic expressions, API for modeling and control of dynamical systems, and extensive set of tutorial code examples in the form of python scripts and jupyter notebooks.

97 MATHEMATICS AND COMPUTING↗