{"id":26728641,"url":"https://github.com/cserajdeep/liquid-neural-network-lnn","last_synced_at":"2025-08-05T06:16:58.709Z","repository":{"id":282362932,"uuid":"948339428","full_name":"cserajdeep/LIQUID-NEURAL-NETWORK-LNN","owner":"cserajdeep","description":"LIQUID NEURAL NETWORK LNN CLASSIFIER AND REGRESSION","archived":false,"fork":false,"pushed_at":"2025-03-14T06:49:29.000Z","size":35,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T22:39:50.333Z","etag":null,"topics":["boston-housing-dataset","boston-housing-price-prediction","classification","classifier","cse-rajdeep","huggingface","iris-dataset","kaggle-dataset","kiit","liquid-neural-networks","lnn-classifier","open-source","regression"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cserajdeep.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":"2025-03-14T06:46:01.000Z","updated_at":"2025-03-18T07:54:38.000Z","dependencies_parsed_at":"2025-03-14T07:42:31.672Z","dependency_job_id":null,"html_url":"https://github.com/cserajdeep/LIQUID-NEURAL-NETWORK-LNN","commit_stats":null,"previous_names":["cserajdeep/liquid-neural-network-lnn"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/cserajdeep/LIQUID-NEURAL-NETWORK-LNN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FLIQUID-NEURAL-NETWORK-LNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FLIQUID-NEURAL-NETWORK-LNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FLIQUID-NEURAL-NETWORK-LNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FLIQUID-NEURAL-NETWORK-LNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cserajdeep","download_url":"https://codeload.github.com/cserajdeep/LIQUID-NEURAL-NETWORK-LNN/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FLIQUID-NEURAL-NETWORK-LNN/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259820785,"owners_count":22916544,"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":["boston-housing-dataset","boston-housing-price-prediction","classification","classifier","cse-rajdeep","huggingface","iris-dataset","kaggle-dataset","kiit","liquid-neural-networks","lnn-classifier","open-source","regression"],"created_at":"2025-03-27T22:36:16.527Z","updated_at":"2025-06-14T13:03:26.189Z","avatar_url":"https://github.com/cserajdeep.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 Run-1 LIQUID NEURAL NETWORK LNN🚀\n\n## True Liquid Time-Constant (LTC) Cell\n\n- Implemented proper continuous-time dynamics with learnable time constants\n- Added decay factor based on tau parameter that controls information flow\n\n---\n\n## Enhanced Architecture\n\n- Multi-layer capability for deeper networks\n- Self-attention mechanism for capturing temporal relationships\n- Skip connections and layer normalization for better gradient flow\n\n---\n\n## Robust Training Framework\n\n- Learning rate scheduling with `ReduceLROnPlateau`\n- Early stopping to prevent overfitting\n- Gradient clipping to prevent exploding gradients\n- AdamW optimizer with weight decay for regularization\n\n---\n\n## Comprehensive Evaluation\n\n- Detailed metrics for both classification and regression\n- Visualization of results (confusion matrices, prediction plots)\n- Feature importance analysis for regression tasks\n\n---\n\n## Hyperparameter Tuning\n\n- Simple grid search to find optimal model configuration\n- Best model checkpointing\n\n---\n\n## Improved Data Handling\n\n- Better error handling for dataset loading\n- Proper input normalization\n- Support for both sequence and non-sequence data formats\n\n---\n\nThe code is now much more robust, handles edge cases better, and should provide significantly better performance on both classification and regression tasks.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcserajdeep%2Fliquid-neural-network-lnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcserajdeep%2Fliquid-neural-network-lnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcserajdeep%2Fliquid-neural-network-lnn/lists"}