{"id":21885017,"url":"https://github.com/saeidemadi/nns","last_synced_at":"2025-03-22T01:40:25.847Z","repository":{"id":244547209,"uuid":"791044098","full_name":"saeidEmadi/NNS","owner":"saeidEmadi","description":"NNS : Neural network surgery  | academic assignment","archived":false,"fork":false,"pushed_at":"2024-06-15T12:48:51.000Z","size":13585,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-26T19:46:45.900Z","etag":null,"topics":["ann","artificial-neural-networks","compression-algorithm","compression-models","compressions","pruning","pruning-algorithms","pruning-structures"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/saeidEmadi.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-24T01:52:33.000Z","updated_at":"2024-06-15T13:03:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"9055b979-df27-4847-a920-4a06f3ad7135","html_url":"https://github.com/saeidEmadi/NNS","commit_stats":null,"previous_names":["saeidemadi/nns"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saeidEmadi%2FNNS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saeidEmadi%2FNNS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saeidEmadi%2FNNS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saeidEmadi%2FNNS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/saeidEmadi","download_url":"https://codeload.github.com/saeidEmadi/NNS/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244894308,"owners_count":20527669,"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":["ann","artificial-neural-networks","compression-algorithm","compression-models","compressions","pruning","pruning-algorithms","pruning-structures"],"created_at":"2024-11-28T10:18:19.183Z","updated_at":"2025-03-22T01:40:25.829Z","avatar_url":"https://github.com/saeidEmadi.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NNS : Neural network surgery\n\u003cp\u003e Transfer learning has emerged as a pivotal approach in machine learning, enabling models to leverage knowledge from one domain\nand apply it to another, often related, domain. Methods like : Pre-trained Models, Feature Extraction,Fine-tuning\n,Multi-task Learning,etc. The use of these methods due to domain dependence, complete and complex transfer of learning\ncauses lack of understanding of the model, high computational cost, negative transfer and very limited application of our\nmodel. With neural network surgery (NNS) and its in-depth investigation, we provide general knowledge about the specific learned\ntopic with full coverage of the topic without bias and inter-neural interference in the process of learning transfer. In this method,\nby taking a deep look at the events in the memory during calculations, as well as labeling them, stimulating the neural network\ncase by case, and comparing the results, we tried to discover and limit the network to that particular label. By removing the less\nimportant connected neurons to the rest of the labels, we have been able to prevent overfitting and also prepare general learning for\ntransfer. By performing surgery on the neural network that has learned the MNIST, we have extracted learning in a special\nway to recognize ”3” labels. Finally, it is possible to transfer learning to the next generations in a simple and easy way and to\nuse it for continuous learning of special labels, and it is also possible to mention the transfer of learning special labels from\nvery complex models with many labels to small models with High accuracy In this research, new interesting results about the\ncompression of neural network models are mentioned.\u003c/p\u003e\n\nIn this article, we tried to perform deep surgeries on neural networks and very interesting results have been obtained\nWe suggest you take a look [Paper Direct Link](https://github.com/saeidEmadi/NNS/blob/main/NNS.pdf)\n\n\u003e [!NOTE]\n\u003e This article and writing is only an academic assignment and has no confirmed scientific validity (it should be noted that the copyright law includes this assignment as well)\n\nThanks to Zahra.D\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaeidemadi%2Fnns","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsaeidemadi%2Fnns","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaeidemadi%2Fnns/lists"}