{"id":23767368,"url":"https://github.com/sccsmartcode/deep-learning-02","last_synced_at":"2026-04-17T06:33:32.014Z","repository":{"id":258146725,"uuid":"869585443","full_name":"SCCSMARTCODE/Deep-Learning-02","owner":"SCCSMARTCODE","description":"This repository contains a collection of deep learning projects focused on sequential data, leveraging Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), GRUs, and other techniques.","archived":false,"fork":false,"pushed_at":"2024-11-19T13:23:06.000Z","size":4109,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-24T00:23:55.853Z","etag":null,"topics":["deep-learning","gru","lstm","natural-language-processing","python","rnn","sequential-data"],"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/SCCSMARTCODE.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,"zenodo":null}},"created_at":"2024-10-08T14:40:37.000Z","updated_at":"2024-12-05T09:18:00.000Z","dependencies_parsed_at":"2025-05-25T13:08:14.770Z","dependency_job_id":"5732c1a2-249e-4528-bb68-37724017cd1c","html_url":"https://github.com/SCCSMARTCODE/Deep-Learning-02","commit_stats":null,"previous_names":["sccsmartcode/deep-learning-02"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SCCSMARTCODE/Deep-Learning-02","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SCCSMARTCODE%2FDeep-Learning-02","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SCCSMARTCODE%2FDeep-Learning-02/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SCCSMARTCODE%2FDeep-Learning-02/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SCCSMARTCODE%2FDeep-Learning-02/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SCCSMARTCODE","download_url":"https://codeload.github.com/SCCSMARTCODE/Deep-Learning-02/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SCCSMARTCODE%2FDeep-Learning-02/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31918592,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T18:22:33.417Z","status":"online","status_checked_at":"2026-04-17T02:00:06.879Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["deep-learning","gru","lstm","natural-language-processing","python","rnn","sequential-data"],"created_at":"2025-01-01T00:37:14.974Z","updated_at":"2026-04-17T06:33:31.995Z","avatar_url":"https://github.com/SCCSMARTCODE.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep-Learning-02: Sequential Data Projects\n\n## Overview\n\nThis repository contains a collection of deep learning projects that focus on **sequential data**. Sequential data can include anything from time series data, text, speech, or even video frames. The key challenge in working with such data is to capture and learn from temporal dependencies. This repository explores various techniques such as **Recurrent Neural Networks (RNNs)**, **Long Short-Term Memory (LSTMs)**, and **Gated Recurrent Units (GRUs)** to build models for handling sequential data.\n\n### Key Techniques:\n- Recurrent Neural Networks (RNNs)\n- Long Short-Term Memory (LSTM)\n- Gated Recurrent Units (GRU)\n- Time Series Forecasting\n- Natural Language Processing (NLP) for sequence modeling\n\n## Table of Contents\n1. [Text Generation with LSTM](#text-generation-with-lstm)\n2. [Time Series Forecasting](#time-series-forecasting)\n3. [Sequence Classification](#sequence-classification)\n4. [Speech Recognition](#speech-recognition)\n\n## - [x] Text Generation with LSTM\n\nIn this project, we explore the task of text generation using a **character-level LSTM** model. The model learns to generate text one character at a time based on a training corpus. By using techniques such as **temperature sampling**, we can control the creativity and randomness of the generated text.\n\n- **Techniques**: Character-level embeddings, LSTM, softmax sampling\n- **Dataset**: Shakespeare's works or any other text corpus\n- **Applications**: Creative text generation, language modeling\n\n**Folder**: `text-generation/`\n\n## - [ ] Time Series Forecasting\n\nThis project explores **time series data** forecasting using deep learning models. We utilize RNNs and LSTMs to predict future values of time series data such as stock prices or weather patterns. The key objective is to model long-term dependencies within the data.\n\n- **Techniques**: LSTM for time series, sliding window approach, sequence-to-sequence models\n- **Dataset**: Stock prices, weather data, or custom time series data\n- **Applications**: Forecasting trends, anomaly detection\n\n**Folder**: `time-series-forecasting/`\n\n## - [x] Sequence Classification\n\nIn this project, we classify sequential data using RNNs and LSTMs. The focus is on sequence classification tasks such as sentiment analysis, where the entire sequence (e.g., a sentence or document) is classified into a category.\n\n- **Techniques**: RNN/LSTM for sequence classification, embeddings\n- **Dataset**: IMDB movie reviews or other sequential data for classification tasks\n- **Applications**: Sentiment analysis, document classification\n\n**Folder**: `sequence-classification/`\n\n## - [ ] Speech Recognition\n\nThis project applies **deep learning** to the task of speech-to-text recognition using sequential models such as LSTMs. We process speech data and learn to transcribe it into text.\n\n- **Techniques**: RNN/LSTM for speech recognition, sequence-to-sequence models, speech data preprocessing\n- **Dataset**: Common Voice dataset, or other open speech datasets\n- **Applications**: Speech-to-text systems, voice assistants\n\n**Folder**: `speech-recognition/`\n\n## How to Use the Code\n\n1. **Clone the repository**:\n   ```bash\n   git clone https://github.com/your-username/Deep-Learning-02.git\n   cd Deep-Learning-02\n   ```\n\n## Future Work\n\n- Addition of more sequential data projects (e.g., video processing, music generation).\n- Experimentation with advanced models like **Transformers** for handling long sequences.\n\n## Contributing\n\nContributions are welcome! Feel free to open an issue or submit a pull request if you want to add a new project or improve an existing one.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsccsmartcode%2Fdeep-learning-02","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsccsmartcode%2Fdeep-learning-02","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsccsmartcode%2Fdeep-learning-02/lists"}