Search Results for "multi-layer perceptron python"

PyTensor is a fork of Aesara, a Python library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays. PyTensor is based on Theano, which has been powering large-scale computationally intensive scientific investigations since 2007. A hackable, pure-Python codebase. Extensible graph framework is suitable for rapid development of custom operators and symbolic optimizations.

* Fast C++ library for linear algebra (matrix maths) and scientific computing * Easy to use functions and syntax, deliberately similar to Matlab / Octave * Uses template meta-programming techniques to increase efficiency * Provides user-friendly wrappers for OpenBLAS, Intel MKL, LAPACK, ATLAS, ARPACK, SuperLU and FFTW libraries * Useful for machine learning, pattern recognition, signal processing, bioinformatics, statistics, finance, etc. * Downloads:...

ViennaCL provides high level C++ interfaces for linear algebra routines on CPUs and GPUs using CUDA, OpenCL, and OpenMP. The focus is on generic implementations of iterative solvers often used for large linear systems and simple integration into existing projects.

DeDAY (Demography Data Analyses) is a tool of analyzing demography data. It supports Gompertz, Weibull and Logistic distributions. DeDay also supports mixed mortality models based on these distribution such as the Gompertz-Makeham distribution. Distributions such as Gompertz describes only age-dependent mortality, which increases over time. Mixed mortality models, such as in Gompertz-Makeham distribution, consider a more general case where mortality is consist of both age-dependent and...

Provide a reference implementation of Moving Taylor Bayesian Regression, a method for nonparametric multi-dimensional function estimation with correlated errors from finite samples, as a Python package based on SciPy

This program generates customizable hyper-surfaces (multi-dimensional input and output) and samples data from them to be used further as benchmark for response surface modeling tasks or optimization algorithms.

NGmp is a C# C++ Java Python VB.NET etc. etc. binding of GMP and MPFR multi-precision number libraries. With support of Microsoft .NET or Novell Mono runtime NGmp will run on mutliple platforms. It is faster than other libraries available on .NET or Mono