{"id":15009547,"url":"https://github.com/anujdutt9/recurrentneuralnetwork","last_synced_at":"2025-04-09T17:24:52.154Z","repository":{"id":79123281,"uuid":"86261045","full_name":"anujdutt9/RecurrentNeuralNetwork","owner":"anujdutt9","description":"Recurrent Neural Network from scratch using Python and Numpy","archived":false,"fork":false,"pushed_at":"2017-03-26T20:13:38.000Z","size":7,"stargazers_count":14,"open_issues_count":0,"forks_count":7,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-03-23T19:38:46.207Z","etag":null,"topics":["numpy","python-3-5","recurrent-neural-networks","rnn"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anujdutt9.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-03-26T20:00:39.000Z","updated_at":"2024-08-02T01:30:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"7a9bcb9d-5270-461d-a3eb-4094196fb1b3","html_url":"https://github.com/anujdutt9/RecurrentNeuralNetwork","commit_stats":{"total_commits":2,"total_committers":1,"mean_commits":2.0,"dds":0.0,"last_synced_commit":"522e919c3f03425cfbc934c5e6934d35d92455d5"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anujdutt9%2FRecurrentNeuralNetwork","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anujdutt9%2FRecurrentNeuralNetwork/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anujdutt9%2FRecurrentNeuralNetwork/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anujdutt9%2FRecurrentNeuralNetwork/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anujdutt9","download_url":"https://codeload.github.com/anujdutt9/RecurrentNeuralNetwork/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248075708,"owners_count":21043635,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["numpy","python-3-5","recurrent-neural-networks","rnn"],"created_at":"2024-09-24T19:26:29.155Z","updated_at":"2025-04-09T17:24:52.119Z","avatar_url":"https://github.com/anujdutt9.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Recurrent Neural Networks\n***This repository contains the code for Recurrent Neural Network from scratch using Python 3 and numpy.***\n\n# Requirements\n**Numpy**\n\n# Sample Output\n```\nError:[ 3.94375112]\nPred:[1 1 1 1 1 1 1 1]\nTrue:[0 0 1 1 0 1 1 1]\n28 + 27 = 255\n------------\nError:[ 3.89378112]\nPred:[0 0 1 0 1 0 1 0]\nTrue:[1 0 0 1 0 0 1 0]\n21 + 125 = 42\n------------\nError:[ 3.80079469]\nPred:[1 1 1 0 1 0 0 1]\nTrue:[1 1 0 1 1 0 0 1]\n100 + 117 = 233\n------------\nError:[ 3.75256184]\nPred:[0 0 0 1 0 0 0 0]\nTrue:[0 0 1 0 0 1 1 1]\n12 + 27 = 16\n------------\nError:[ 3.47163732]\nPred:[0 0 0 1 0 1 0 1]\nTrue:[0 1 0 1 1 1 0 1]\n67 + 26 = 21\n------------\nError:[ 3.46614289]\nPred:[1 1 1 0 0 1 1 0]\nTrue:[1 0 0 0 0 1 1 0]\n92 + 42 = 230\n------------\nError:[ 0.57723326]\nPred:[0 1 1 1 0 1 1 0]\nTrue:[0 1 1 1 0 1 1 0]\n86 + 32 = 118\n------------\nError:[ 0.83430643]\nPred:[1 1 1 0 1 0 1 0]\nTrue:[1 1 1 0 1 0 1 0]\n107 + 127 = 234\n------------\nError:[ 0.50010502]\nPred:[0 0 1 0 1 0 0 0]\nTrue:[0 0 1 0 1 0 0 0]\n15 + 25 = 40\n------------\nError:[ 0.42438922]\nPred:[0 1 1 1 0 1 1 1]\nTrue:[0 1 1 1 0 1 1 1]\n28 + 91 = 119\n------------\n```\n\n**Note that the RNN keeps on training, predicting output values and collecting dJdW2 and dJdW1 values at each output stage. Once it reaches the last stage of an addition, it starts backpropagating all the errors till the first stage. Hence, after initial 3-4 steps it starts predicting the accurate output.**\n\n# Resources\n\n| S.No.  |                       Papers / Blogs / Authors            |                        Paper Links                   |\n| ------ | --------------------------------------------------------- | ---------------------------------------------------- |\n|1.      |\"A Critical Review of RNN for Sequence Learning\" by Zachary C. Lipton|    https://arxiv.org/pdf/1506.00019.pdf    |\n|2.      |                    \"i am trask\" Blog                      |https://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/|\n|3.      |                  Nikhil Buduma's Blog                     |http://nikhilbuduma.com/2015/01/11/a-deep-dive-into-recurrent-neural-networks/|\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanujdutt9%2Frecurrentneuralnetwork","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanujdutt9%2Frecurrentneuralnetwork","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanujdutt9%2Frecurrentneuralnetwork/lists"}