{"id":13444066,"url":"https://github.com/taolei87/rcnn","last_synced_at":"2025-04-06T09:07:33.176Z","repository":{"id":37735972,"uuid":"48147779","full_name":"taolei87/rcnn","owner":"taolei87","description":"Recurrent \u0026 convolutional neural network modules","archived":false,"fork":false,"pushed_at":"2018-08-16T21:40:05.000Z","size":118761,"stargazers_count":353,"open_issues_count":8,"forks_count":129,"subscribers_count":22,"default_branch":"master","last_synced_at":"2025-03-30T07:11:18.332Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/taolei87.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2015-12-17T02:34:28.000Z","updated_at":"2025-03-01T06:08:57.000Z","dependencies_parsed_at":"2022-08-24T16:00:27.393Z","dependency_job_id":null,"html_url":"https://github.com/taolei87/rcnn","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taolei87%2Frcnn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taolei87%2Frcnn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taolei87%2Frcnn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taolei87%2Frcnn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/taolei87","download_url":"https://codeload.github.com/taolei87/rcnn/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247457800,"owners_count":20941906,"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":[],"created_at":"2024-07-31T03:02:18.127Z","updated_at":"2025-04-06T09:07:33.153Z","avatar_url":"https://github.com/taolei87.png","language":"Python","funding_links":[],"categories":["Python","Uncategorized"],"sub_categories":["Uncategorized"],"readme":"### Latest updates\nCheck [code/rationale](/code/rationale) for the project of learning rationales for neural prediction:  \u003cp align=\"center\"\u003e\n\u003cimg height =140 src=\"code/rationale/figures/example.png\"\u003e \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u003cimg width=350 src=\"code/rationale/figures/model_framework.png\"\u003e\n\n\n[Adam Yala](https://github.com/yala/) has implemented a **Pytorch** version of the rationale project! \n\nCheck it out at: https://github.com/yala/text_nn\n\n\u003c/p\u003e\n\n-------\n\n#### About this repo\nThis repo contains Theano implementations of popular neural network components and optimization methods. Source code of the following papers are also available:\n\n  [1] [Molding CNNs for text: non-linear, non-consecutive convolutions](http://arxiv.org/abs/1508.04112). EMNLP 2015\n  \n  [2] [Semi-supervised Question Retrieval with Gated Convolutions](http://arxiv.org/abs/1512.05726). NAACL 2016\n\n  [3] [Rationalizing Neural Predictions](https://people.csail.mit.edu/taolei/papers/emnlp16_rationale.pdf). EMNLP 2016\n\n#### Features\n  - Basic modules including feedforward layer, dropout, word embedding, RNN, LSTM, GRU and CNN\n  - Optimization methods including SGD, AdaGrad, AdaDelta and Adam\n  - Advanced modules from recent papers such as attention and gated convolution.\n  - Transparent to use GPU\n\n-------\n\n#### Projects\n\n###### 1. Neural question retrieval for community-based QA\n\nThe directories [code/qa](/code/qa) and [code/pt](/code/pt) contain the implementation of the model described in paper [[2]](http://arxiv.org/abs/1512.05726). Datasets and and pre-trained word vectors are available at [here](https://github.com/taolei87/askubuntu).\n\n###### 2. Sentiment analysis / document classification\n\nThe directory [code/sentiment](/code/sentiment) contains the implementation of the model described in paper [[1]](http://arxiv.org/abs/1508.04112). Datasets and and pre-trained word vectors are available at [here](https://github.com/taolei87/text_convnet).\n\n###### 3. Rationalizing neural predictions\n\nThe directory [code/rationale](/code/rationale) contains the implementation of the model described in paper [[3]](https://people.csail.mit.edu/taolei/papers/emnlp16_rationale.pdf).\n\n-------\n\n#### Dependencies\n  [Theano](http://deeplearning.net/software/theano/) \u003e= 0.7, Python \u003e= 2.7, Numpy\n\n-------\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftaolei87%2Frcnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftaolei87%2Frcnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftaolei87%2Frcnn/lists"}