pratyan
@National Institute of Technology Agartala #ML #BlockChain_enthusiast #solidity & RUST #web3.js #SEEK_Python
Pinned Repositories
AFFINE_Transformation_onMNIST
Applied Affine Transformation on MNIST dataset .
Bayasian_LogisticRegression_on_Mnist
Applied Bayesian Logistic Regression approach on Mnist dataset
Blockchain_CosmosSDK_IgniteCLI
Deployed a POS Blockchain using Cosmos SDK framework.
bomb-dashboard-PratyanMajumder
CrowdFunding_in_ELROND
Built a Crowdfunding program for ELrond Blockchain.
Cryptodxc
Crypto-Trading platform X Gpay X Instant Loan
DARKnes
DARKneuron
Denoising_using_FFT
Denoising a signal with "Fast Fourier Transform" algorithm.
web3_py_SimpleStorage
deploying contract using solcx in python to ganache local blockchain
pratyan's Repositories
pratyan/web3_py_SimpleStorage
deploying contract using solcx in python to ganache local blockchain
pratyan/AFFINE_Transformation_onMNIST
Applied Affine Transformation on MNIST dataset .
pratyan/Bayasian_LogisticRegression_on_Mnist
Applied Bayesian Logistic Regression approach on Mnist dataset
pratyan/Blockchain_CosmosSDK_IgniteCLI
Deployed a POS Blockchain using Cosmos SDK framework.
pratyan/bomb-dashboard-PratyanMajumder
pratyan/CrowdFunding_in_ELROND
Built a Crowdfunding program for ELrond Blockchain.
pratyan/Cryptodxc
Crypto-Trading platform X Gpay X Instant Loan
pratyan/DARKneuron
pratyan/Denoising_using_FFT
Denoising a signal with "Fast Fourier Transform" algorithm.
pratyan/elastic_weight_consolidation
Description Neural networks work on the principal of gradient descent by which weights are continously updated as the model trains on the data. In real life scenerios, as datasets grows large, training the data can be painfully complex. One of the methods to overcome this can be, continual learning, in which, the model tries to retain priorly learned informations while still learning the newly learned data. But the problem arises as normal gradient descent drastically modifies the weights of the priorly learned weights. Though implementation of L2 regularization helps, to some extent, but as we continue to train the model over new new datasets, the prior accuracies drops drastically. So we impelemented a technique called Elastic weight consolidation, that helps us to train the model, keeping the prior knowledge intact.
pratyan/Global_board
A Web3.js application powered by react.js and Soilidity (React-Dapp). 'Global Board' is an application where individuals can write their words which will remain listed on the blockchain and displayed for eternity.
pratyan/Helmet_detaction_Using_YOLO-V3
What is YOLOv3? YOLOv3 (You Only Look Once, Version 3) is a real-time object detection algorithm that identifies specific objects in videos, live feeds, or images. YOLO uses features learned by a deep convolutional neural network to detect an object.
pratyan/INEmergency
Emergency! Get instant help, Our application will recommend you the best hospital through a machine learning prediction with a simple click and ensure you a confirmed bed even before your arrival.
pratyan/InvoiceData_Ethereum
Dapp to store invoice data(BuyerPAN, SellerPan, Amount, etc) in blockchain. And can be further accessed or updated as per requirement.
pratyan/LeNet-5_Keras_onMNIST
Applied LeNet-5 CNN architecture on MNIST dataset.
pratyan/LeNet5_ImageClassification
pratyan/MNIST_AFFINE_Trans_withKERAS
Applied Affine Transformation on MNIST dataset before training with KERAS model.
pratyan/MNIST_SparseCategoricalCrossentropy_NORMALCDF_KERAS
APPLIED SparseCategoricalCrossentropy as loss with ADAM optimizer and NORMALCDF as activation on MNIST datasets.
pratyan/NetworkProgramming_Golang
Basic Network Programming using golang. Used webSockets and Goroutines for multiple handlers at a time.
pratyan/NFT_MintingSite_Solana-CandyMachine-v2
Build a NFT Minting site in solana blockchain, using candy machine v2 framework.
pratyan/NFTMarketPlace_Ethereum
Built a NFT market place in Ethereum.
pratyan/RL
All the RL related projects
pratyan/StakingDapp_ChainLink_Synthex
Building a staking dapp using chainlink. The staking algorithm is based on the synthex protocol.
pratyan/Stellar_sdk_001
All the basic operation for "Stellar" Blockchain with "Stellar_sdk" and "horizon" API Endpoint. In python language
pratyan/Storage_with_Solidity
Making a simple 'Storage' web3 application powered by ethereum smart contract(Solidity).
pratyan/SVD-in-ImageCompression-
In this method, digital image is given to SVD. SVD refactors the given digital image into three matrices. Singular values are used to refactor the image and at the end of this process, image is represented with smaller set of values, hence reducing the storage space required by the image.
pratyan/SVM_radial_basis_func_KERNEL
In machine learning, the radial basis function kernel, or RBF kernel, is a popular kernel function used in various kernelized learning algorithms. In particular, it is commonly used in support vector machine classification.
pratyan/SVM_SupportVectors_of_GenClus
Support Vector Machine or SVM is one of the most popular Supervised Learning algorithms, which is used for Classification as well as Regression problems. However, primarily, it is used for Classification problems in Machine Learning.
pratyan/TransferLearning_with_Mobilenet_on_CIFAR10
Used Transfer Learning on Mobilenet(CNN) and trained the pre-trained model with CIFAR10 dataset after Preprocessing it through the Mobilenet_pipline.
pratyan/Voting_with_solidity
A contract for voting purpose.