{"id":17323079,"url":"https://github.com/danieleds/qc_with_untrained_recurrent_embeddings","last_synced_at":"2025-08-01T00:31:41.144Z","repository":{"id":62117533,"uuid":"188004003","full_name":"danieleds/qc_with_untrained_recurrent_embeddings","owner":"danieleds","description":"Question Classification with Untrained Recurrent Embeddings","archived":false,"fork":false,"pushed_at":"2022-10-26T16:56:53.000Z","size":30,"stargazers_count":3,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-10-18T21:56:27.985Z","etag":null,"topics":["echo-state-networks","machine-learning","neural-networks","question-classification","reservoir-computing"],"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/danieleds.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}},"created_at":"2019-05-22T09:14:53.000Z","updated_at":"2023-01-24T09:27:58.000Z","dependencies_parsed_at":"2022-10-26T18:00:46.296Z","dependency_job_id":null,"html_url":"https://github.com/danieleds/qc_with_untrained_recurrent_embeddings","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danieleds%2Fqc_with_untrained_recurrent_embeddings","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danieleds%2Fqc_with_untrained_recurrent_embeddings/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danieleds%2Fqc_with_untrained_recurrent_embeddings/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danieleds%2Fqc_with_untrained_recurrent_embeddings/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/danieleds","download_url":"https://codeload.github.com/danieleds/qc_with_untrained_recurrent_embeddings/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228320961,"owners_count":17901599,"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":["echo-state-networks","machine-learning","neural-networks","question-classification","reservoir-computing"],"created_at":"2024-10-15T13:45:17.464Z","updated_at":"2024-12-05T14:41:43.603Z","avatar_url":"https://github.com/danieleds.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"This repository contains the code for the following paper:\n\n\"[Question Classification with Untrained Recurrent Embeddings](http://for.unipi.it/daniele_di_sarli/files/2019/11/paper_54.pdf)\",  \nD. Di Sarli, C. Gallicchio, A. Micheli,  \nAI*IA 2019 – Advances in Artificial Intelligence.\n\n## Running\n\nThe folder structure is organized on two levels.\nAt the top level we have the dataset (QC), and inside that folder\nwe have the models applied to that dataset.\n\nTo launch an experiment, for example a leaky ESN on the QC task, run this command\nfrom the root of the project:\n\n    $ python3 QC/leaky_esn  # ...args...\n\n## Reproducing results\n\nTo reproduce the results in the paper, just run the following commands:\n\n    $ python3 QC/leaky_esn --searches 0 --final-trials 10\n    $ python3 QC/leaky_esn_ensemble --searches 0 --final-trials 10\n    $ python3 QC/leaky_esn_attn --searches 0 --final-trials 10\n    $ python3 QC/mygru --searches 0 --final-trials 10\n\n## Hardware\n\nIt is advisable to run the code on a GPU with at least 16GB of memory. Alternatively, the code\ncan easily be modified to accumulate the gradients of smaller minibatches in the training loop.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanieleds%2Fqc_with_untrained_recurrent_embeddings","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdanieleds%2Fqc_with_untrained_recurrent_embeddings","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanieleds%2Fqc_with_untrained_recurrent_embeddings/lists"}