There are no reviews yet. Be the first to send feedback to the community and the maintainers!
deep-voice-conversion
What if you could imitate a famous celebrity's voice or sing like a famous singer? This project started with a goal to convert someone's voice to a specific target voice. So called, it's voice style transfer. We worked on this project that aims to convert someone's voice to a famous English actress Kate Winslet's voice. We implemented a deep neural networks to achieve that and more than 2 hours of audio book sentences read by Kate Winslet are used as a dataset.rough_surfaces
Computational mechanics for rough surfaces and fracturesAwesomeFortranLibraries
This is a collection of Fortran routines written by Sourangshu Ghosh over the years for use in more complex codes. The different files are as independent as possible from each other, but in some cases dependencies are unavoidable.Stochastic_LatentDirchletAnalysis
Python implementation of Stochastic Variational Inference for LDASeismicAnalyzer
SEISMIC_CPML is a set of sixteen open-source Fortran90 programs to solve the two-dimensional or three-dimensional isotropic or anisotropic elastic, viscoelastic or poroelastic wave equation using a finite-difference method with Convolutional or Auxiliary Perfectly Matched Layer (C-PML or ADE-PML) conditionsFiniteElementAnalysis
A Simple Finite Element Method programBitCoinPricepredictor
Bitcoin price prediction algorithm using bayesian regression techniquesSourangshuGhosh
Sourangshu Ghosh Readme FileSteel_Sections_Properties
A Python software able to calculate the cross-section properties of combined steel sectionsCGP-CNN-Design
A Genetic Programming Approach to Designing CNN Architectures, In GECCO 2017 (oral presentation, Best Paper Award)allen_cahn_ode
allen_cahn_ode, a Python code by Sourangshu Ghosh which sets up and solves the 1D Allen-Cahn reaction-diffusion ordinary differential equation (ODE).100_ComputerScience_Papers
100 Computer Science Papers listed by Sourangshu GhoshDoubly-Stochastic-Deep-Gaussian-Process
Gaussian processes (GPs) are a good choice for function approximation as they are flexible, robust to over-fitting, and provide well-calibrated predictive uncertainty. Deep Gaussian processes (DGPs) are multi-layer generalisations of GPs, but inference in these models has proved challenging. Existing approaches to inference in DGP models assume approximate posteriors that force independence between the layers, and do not work well in practice. We present a doubly stochastic variational inference algorithm, which does not force independence between layers. With our method of inference we demonstrate that a DGP model can be used effectively on data ranging in size from hundreds to a billion points. We provide strong empirical evidence that our inference scheme for DGPs works well in practice in both classification and regression.Bag-of-words-Model
The bag-of-words model is a simplifying representation used in natural language processing and information retrieval (IR). In this model, a text (such as a sentence or a document) is represented as the bag (multiset) of its words, disregarding grammar and even word order but keeping multiplicity.N-gram
An n-gram model is a type of probabilistic language model for predicting the next item in such a sequence in the form of a (n − 1)–order Markov model.Optimization_Bayesian.jl
Bayesian optimization is a method of finding the maximum of expensive cost functions. Bayesian optimization employs the Bayesian technique of setting a prior over the objective function and combining it with evidence to get a posterior function. This permits a utility-based selection of the next observation to make on the objective function, which must take into account both exploration (sampling from areas of high uncertainty) and exploitation (sampling areas likely to offer improvement over the current best observation).coronavirus_cure_DeepLearning
Using deep learning to generate novel molecules as candidates for binding with coronavirus proteaseGaussianProcessMotionPlanner
Gaussian Process Motion PlannerQuantumComputing
This is an implementation of IBM's Quantum Experience in simulation; a 5-qubit quantum computer with a limited set of gates.Fluid-Simulation-for-Computer-Graphics
A PIC/FLIP fluid simulation based on the methods found in Robert Bridson's "Fluid Simulation for Computer Graphics"Evolutionary-Deep-Neural-Network
This is a software code for Evolutionary Deep Neural Network. Evolutionary Deep Neural Networks train neural networks using an evolutionary algorithmStochastic_Reactive_Brownian_Dynamics
A Fortran 95 Implementation of Stochastic Reactive Brownian Dynamics particle method for reaction-diffusion problems decribed in the paper "Efficient Reactive Brownian Dynamics" by A.DonevMachineLearning_Predicting_Adverse_Drug_Reactions
The objective of this work by Sourangshu Ghosh was to develop machine learning methods that could accurately predict adverse drug reactions using the SIDER and OFFSIDEs databases.Stochastic_Seismic_Generator
A C++ software useful for generating the seismic ground motion with inputs of Distance, fault dimensions, orientation and soil profile on origin and siteCovid19_SIRModel2
Simulating coronavirus with the SIR modelFuzzyCMean
Fuzzy clustering is a form of clustering in which each data point can belong to more than one cluster. Clustering or cluster analysis involves assigning data points to clusters such that items in the same cluster are as similar as possible, while items belonging to different clusters are as dissimilar as possibleGeneticProgramming-in-C
Genetic Programming in C++StructuralReliability
A Python code useful for determining the Reliability of Weld Joints in Operational Nuclear Reactorstacs
Finite-element library for analysis and adjoint-based gradient evaluationMarkovChainTest
Python utility that uses a Markov Chain to generate random sentences using a source textburgers_time_viscous
burgers_time_viscous, a FENICS code by Sourangshu Ghosh which uses the finite element method to solve a version of the time-dependent viscous Burgers equation over the interval [-1,+1].VariationalAutoencoder
An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner.The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for dimensionality reduction, by training the network to ignore signal “noise”. Along with the reduction side, a reconstructing side is learnt, where the autoencoder tries to generate from the reduced encoding a representation as close as possible to its original input, hence its name. Several variants exist to the basic model, with the aim of forcing the learned representations of the input to assume useful properties. Examples are the regularized autoencoders (Sparse, Denoising and Contractive autoencoders), proven effective in learning representations for subsequent classification tasks,and Variational autoencoders, with their recent applications as generative models. Autoencoders are effectively used for solving many applied problems, from face recognition to acquiring the semantic meaning of wordsNeuralTuringMachine
This repository contains a stable, successful Tensorflow implementation of a Neural Turing Machine which has been tested on the Copy, Repeat Copy and Associative Recall tasks from the original paper.Annulus_flow_FENICS
Annulus_flow, a FENICS code by Sourangshu Ghosh which models the flow of a fluid, governed by the time dependent Navier-Stokes equations, in a 2D eccentric annulus.Bash2048
2048 is a single-player sliding block puzzle game designed by Italian web developer Gabriele Cirulli. The objective of the game is to slide numbered tiles on a grid to combine them to create a tile with the number 2048; however, one can continue to play the game after reaching the goal, creating tiles with larger numbers. It was originally written in JavaScript and CSS over a weekend, and released on 9 March 2014 as free and open-source software subject to the MIT license. This repository is written by Sourangshu Ghosh in Bash.Reverse-Cuthill-McKee-Ordering-in-C
RCM is a C++ library which computes the Reverse Cuthill McKee ("RCM") ordering of the nodes of a graph. The RCM ordering is frequently used when a matrix is to be generated whose rows and columns are numbered according to the numbering of the nodes. By an appropriate renumbering of the nodes, it is often possible to produce a matrix with a much smaller bandwidth.The bandwidth of a matrix is computed as the maximum bandwidth of each row of the matrix. The bandwidth of a row of the matrix is essentially the number of matrix entries between the first and last nonzero entries in the row, with the proviso that the diagonal entry is always treated as though it were nonzero.This library includes a few routines to handle the common case where the connectivity can be described in terms of a triangulation of the nodes, that is, a grouping of the nodes into sets of 3-node or 6-node triangles. The natural description of a triangulation is simply a listing of the nodes that make up each triangle. The library includes routines for determining the adjacency structure associated with a triangulation, and the test problems include examples of how the nodes in a triangulation can be relabeled with the RCM permutation.SteinVariationalGradientDescent-SVGD-
SVGD is a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization. SVGD iteratively transports a set of particles to match with the target distribution, by applying a form of functional gradient descent that minimizes the KL divergence.test
Sourangshu.github.io
My Personal WebsiteRadhaKrishna.github.io
A Site meant for discussion of Krishna Consciousness among Vaishnava Devotees Jointly Hosted by HG Rathin Singha Pr. and Sourangshu Ghosh anBasic-Linear-Algebra-Subprograms
A library created by Sourangshu Ghosh which contains the Basic Linear Algebra Subprograms (BLAS) for level 1, 2 and 3, for single and double precision, and for real and complex arithmetic.py-bbn
Inference in Bayesian Belief Networks using Probability Propagation in Trees of Clusters (PPTC) and Gibbs samplingSteelSections
A Matlab GUI( Graphical User Interface) which is helpful for designing structural members under given load conditionsCovid-19_Model
The superiority and inferiority ranking method (or SIR method) is a multi-criteria decision making model (MCDA) which can handle real data and provides six different preference structures for the system user.VIforSDEs
FORM
First Order Reliability Methods. Taylor series approximation of the performance function of different stochastic variables.bvp
bvp, FENICS codes by Sourangshu Ghosh which use the finite element method to solve two point boundary value problems (BVP) over an interval in 1D.Stochastic-Outlier-Selection-SOS-
Stochastic-Outlier-Selection-SOS is a Python module by Sourangshu Ghosh for Stochastic Outlier Selection (SOS). It is compatible with scikit-learn. SOS is an unsupervised outlier selection algorithm. It uses the concept of affinity to compute an outlier probability for each data point.burgers_steady_viscous_FENICS
burgers_steady_viscous, a FENICS code which uses the finite element method to solve a version of the steady viscous Burgers equation over the interval [-1,+1].AbstractGPs.jl
AbstractGPs.jl is a package that defines a low-level API for working with Gaussian processes (GPs), and basic functionality for working with them in the simplest cases. As such it is aimed more at developers and researchers who are interested in using it as a building block than end-users of GPs.Reverse-Cuthill-McKee-Ordering
In numerical linear algebra, the Cuthill–McKee algorithm (CM), named for Elizabeth Cuthill and James McKee, is an algorithm to permute a sparse matrix that has a symmetric sparsity pattern into a band matrix form with a small bandwidth. The reverse Cuthill–McKee algorithm (RCM) due to Alan George is the same algorithm but with the resulting index numbers reversedAlpert_Rule_C
ALPERT_RULE is a C library which has tabulated values that define Alpert quadrature rules of a number of orders of accuracy for functions that are regular, log singular, or power singular.Jigsaw-Solver
A jigsaw puzzle solver for randomly shuffled square shaped images.ALPERT_RULE_F90
ALPERT_RULE, a FORTRAN90 library which has tabulated values that define Alpert quadrature rules of a number of orders of accuracy for functions that are regular, log singular, or power singular.ANAGRAM
ANAGRAM, a C++ program which takes a string of letters and tries to produce as many anagrams as possible.Ascendogram_Fortran
The Ascendogram Puzzle by Sourangshu GhoshBESSELJ
BESSELJ, a Python library which evaluates Bessel J functions of noninteger order.Alpert_Rule_Matlab
ALPERT_RULE, a MATLAB library which has tabulated values that define Alpert quadrature rules of a number of orders of accuracy for functions that are regular, log singular, or power singular.ChrisEDignall.github.io
Reverse-Cuthill-McKee-Ordering-in-F90
The Cuthill-Mckee algorithm is used for the reordering of a symmetric square matrix. It is based on the Breadth-First Search algorithm of a graph, whose adjacency matrix is the sparsified version of the input square matrix.The ordering is frequently used when a matrix is to be generated whose rows and columns are numbered according to the numbering of the nodes. By an appropriate renumbering of the nodes, it is often possible to produce a matrix with much smaller bandwidth. The Sparsified version of a matrix is a matrix in which most of the elements are zero.The Reverse Cuthill-Mckee Algorithm is the same as the Cuthill-Mckee algorithm, the only difference is that the final indices obtained using the Cuthill-Mckee algorithm are reversed in the Reverse Cuthill-Mckee Algorithm.OR_Lab
Assignment Solutions of OR_Lab IIT KGPLove Open Source and this site? Check out how you can help us