Search Results for "automatic differentiation" - Page 3
Sort By:
Showing 75 open source projects for "automatic differentiation"
View related business solutions-
Streamline Azure Security with Palo Alto Networks VM-SeriesImprove your security posture and reduce incident response time. Use the VM-Series to natively analyze Azure traffic and dynamically drive policy updates based on workload changes.
-
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
RigidBodyDynamics.jl
Julia implementation of various rigid body dynamics
...However, if symbolic quantities are desired for analysis purposes, they can be obtained by calling the algorithms with e.g. SymPy.Sym inputs. If gradients are required, e.g. the ForwardDiff.Dual type, which implements forward-mode automatic differentiation, can be used. -
2
Swift for TensorFlow
Swift for TensorFlow
...The initiative aims to provide a new programming model for developing machine learning systems by combining the power of TensorFlow with language-level features such as automatic differentiation and strong type systems. By embedding machine learning functionality into the Swift compiler and language design, the project enables developers to write high-performance machine learning models while maintaining the readability and safety of modern programming practices. Swift for TensorFlow also introduces tools that allow developers to compute gradients automatically, which is essential for training neural networks through gradient-based optimization. -
3
gradslam
gradslam is an open source differentiable dense SLAM library
...However, learning representations for SLAM has been an open question, because traditional SLAM systems are not end-to-end differentiable. In this work, we present gradSLAM, a differentiable computational graph take on SLAM. Leveraging the automatic differentiation capabilities of computational graphs, gradSLAM enables the design of SLAM systems that allow for gradient-based learning across each of their components, or the system as a whole. -
4
micrograd
A tiny scalar-valued autograd engine and a neural net library
micrograd is a tiny, educational automatic differentiation engine focused on scalar values, built to show how backpropagation works end to end with minimal code. It constructs a dynamic computation graph as you perform math operations and then computes gradients by walking that graph backward, making it an approachable “from scratch” autograd reference. On top of the core autograd “Value” concept, the project includes a small neural network library that lets you define and train simple models with a PyTorch-like feel, including multilayer perceptrons. ... -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
5
CrypTen
A framework for Privacy Preserving Machine Learning
...Designed to make secure computation accessible to machine learning practitioners, CrypTen introduces a CrypTensor object that behaves like a regular PyTorch tensor, allowing users to seamlessly apply automatic differentiation and neural network operations. Its design mirrors PyTorch’s modular and library-based structure, enabling flexible experimentation, debugging, and model development. The framework supports both encryption and decryption of tensors and operations such as addition and multiplication over encrypted values. Although not yet production-ready, CrypTen focuses on advancing real-world secure ML applications, such as training and inference over private datasets, without exposing sensitive data. -
6
AdaAutoDiff
C++ Templates and Ada Package for Automatic Differentiation
Operators are overloaded so that a normal looking function definition provides access to not only evaluations of itself, but to evaluations of any of its analytic derivatives. Automatic differentiation means the user does not need to define the analytic expressions for all the various partial derivatives. It also means that those complex expressions are essentially calculated at compile time, and merely evaluated at runtime. First order derivatives only, forward accumulation. Choose "files" and either the "initial_submission" directory for the Ada version, or the other directory "cpp_AD" for the C++ version. -
7
A symbolic framework for C++, Python and Octave implementing automatic differentiation by source code transformation in forward and reverse modes on sparse matrix-valued computational graphs.
-
8
TF Quant Finance
High-performance TensorFlow library for quantitative finance
...It implements pricing engines, risk measures, stochastic models, optimizers, and random number generators that are differentiable and vectorized for accelerators. Users can value options and fixed-income instruments, simulate paths, fit curves, and calibrate models while leveraging TensorFlow’s jit compilation and automatic differentiation. The codebase is organized as modular math and finance primitives so you can combine building blocks or target end-to-end examples. It includes Bazel builds, tests, and example notebooks to accelerate learning and adoption in real workflows. With hardware acceleration and differentiable models, it enables modern techniques like gradient-based calibration and end-to-end learning of market dynamics. -
9
ADiGator
A MATLAB Automatic Differentiation Tool
ADiGator is a source transformation via operator overloading tool for the automatic differentiation of mathematical functions written in MATLAB. Given a user written file, together with information on the inputs of said file, ADiGator uses forward mode automatic differentiation to generate a new file which contains the calculations required to compute the numeric derivatives of the original user function. Furthermore, these calculations are written entirely in the native MATLAB language, and thus the process may be repeated to obtain nth order derivative files. ... -
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
10
Microsoft Cognitive Toolkit (CNTK)
Open-source toolkit for commercial-grade distributed deep learning
CNTK describes neural networks as a series of computational steps via a digraph which are a set of nodes or vertices that are connected with the edges directed between different vertexes. Create and combine models such as: -Feed-Forward DNNs -Convolutional neural networks -Recurrent neural networks -
11
OpenOCL Matlab
Optimal control, trajectory optimization, model-predictive control.
The Open Optimal Control Library is a software framework in Matlab/Octave for modeling optimal control problem. It uses automatic differentiation and fast non-linear programming solvers. It implements direct methods. In the backend it uses CasADi and ipopt. -
12
NimTorch
PyTorch - Python + Nim
NimTorch is a deep learning library for the Nim programming language, providing bindings to PyTorch for efficient tensor computations and neural network functionalities. -
13
Edward
A probabilistic programming language in TensorFlow
...Edward fuses three fields, Bayesian statistics and machine learning, deep learning, and probabilistic programming. Edward is built on TensorFlow. It enables features such as computational graphs, distributed training, CPU/GPU integration, automatic differentiation, and visualization with TensorBoard. Expectation-Maximization, pseudo-marginal and ABC methods, and message passing algorithms. -
14
Tangent
Source-to-source debuggable derivatives in pure Python
Existing libraries implement automatic differentiation by tracing a program's execution (at runtime, like PyTorch) or by staging out a dynamic data-flow graph and then differentiating the graph (ahead-of-time, like TensorFlow). In contrast, Tangent performs ahead-of-time autodiff on the Python source code itself, and produces Python source code as its output. Tangent fills a unique location in the space of machine learning tools. -
15
Chebfun
Chebfun: numerical computing with functions
Chebfun is a MATLAB-based system for numerical computing with functions instead of just numbers. It represents functions using Chebyshev polynomial approximations and allows users to perform operations like differentiation, integration, root finding, and solving ODEs using symbolic-like syntax. Chebfun simplifies working with continuous mathematics using high-accuracy numerical techniques. -
16
autodiff
Python class for automatic differentiation
Python automatic differentiation class for forward mode automatic differentiation using operator overloading and reimplemented math functions. Single and partial derivatives are supported. Supported operators: +, -, *, /, **, +=, -=, *=, /=, **= Available functions: sin, cos, tan, asin, acos, atan, sqrt, exp, log, log10, sinh, cosh, tanh, asinh, acosh, atanh See README file for usage examples. -
17
RStan
RStan, the R interface to Stan
...Key inference approaches include full Bayesian inference via Hamiltonian Monte Carlo (specifically the No-U-Turn Sampler, NUTS), approximate Bayesian inference via variational methods, and optimization (penalized likelihood). RStan integrates with Stan’s automatic differentiation library, provides diagnostics, model comparison, posterior predictive checks, etc. It is used in research, applied statistics, and modelling workflows where flexibility and rigor in Bayesian methods are required. -
18
GADfit
Global nonlinear optimization with automatic differentiation
...Global fitting refers to fitting many datasets simultaneously with some parameters shared among the datasets. The fitting procedure is very fast and accurate thanks to the use of automatic differentiation. The model curves (fitting functions) can be of essentially arbitrary complexity. This includes any nonlinear combination of elementary and special functions, single and/or double integrals, and any control flow statement allowed by the programming language. See the latest user guide under Files. -
19
TIDES
Taylor series Integrator for Differential Equations
Taylor series Integrator for Differential EquationS. This software is developed by Profs. A. Abad, R. Barrio, F. Blesa and M. Rodriguez, (GME, University of Zaragoza, Spain). It consists on a C (Fortran) library, libTIDES, and a Mathematica package, MathTIDES. (MathTIDES requires Mathematica version >= 7.0) . Basic references: * A. Abad, R. Barrio, F. Blesa, M. Rodriguez, 2012. Algorithm 924: TIDES, a Taylor series Integrator for Differential EquationS, ACM TOMS. 39, no. 1, art. 5.... -
20
ANGEL-Automatic differentiation Nested Graph Elimination Library is a template library using the Boost Graph Library and the Standard C++ Library; it provides sparse representations of c-graphs their dual line graphs and vertex, edge and face elimina
-
21
GPDC
Gravity Potential Derivatives Calculator
GPDC is a C file to compute partial derivatives of a gravity potential up to any order by means of an automatic differentiation method. -
22
A 2-D inviscid flow and adjoint solver on unstructured triangular grids. It makes use of a vertex-centroid finite volume scheme which is second order accurate. The adjoint solver is developed using the automatic differentiation tool called TAPENADE. Code has been moved to https://github.com/cpraveen/euler2d
-
23
-
24
ADMC++ -- An Automatic Differentiation Package for MATLAB and C++ ADMC++ is an automatic differentiation package designed for MATLAB and C++. Automatic differentiation is a technique for computing derivatives of functions.
-
25
Dokio
Free personal cloud service for small businesses.
...Create products, register sales, store contacts of counterparties, control payments and trade efficiency. Maintaining customer orders, the ability to reserve goods, automatic removal of reserves when selling. Monitoring of sales volumes of each department or employee by goods or categories of goods for any period of time. Control of in-stock balances in real-time mode, the ability to set minimal balances for each warehouse. Differentiation of users by roles - you can give your employees only the access rights according to their work. ...
