{"id":17741790,"url":"https://github.com/aakashns/deep-learning-workbook","last_synced_at":"2026-03-03T02:31:43.406Z","repository":{"id":134698592,"uuid":"115523260","full_name":"aakashns/deep-learning-workbook","owner":"aakashns","description":"A universal workflow for solving machine learning problems","archived":false,"fork":false,"pushed_at":"2022-10-27T11:34:53.000Z","size":211,"stargazers_count":16,"open_issues_count":0,"forks_count":8,"subscribers_count":1,"default_branch":"master","last_synced_at":"2023-03-10T11:26:13.296Z","etag":null,"topics":["deep-learning","jupyter-notebook","keras","machine-learning","tensorflow"],"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/aakashns.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":"2017-12-27T13:21:50.000Z","updated_at":"2022-10-27T08:35:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"d45f97a3-29d2-458d-8bb6-1505a8390445","html_url":"https://github.com/aakashns/deep-learning-workbook","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/aakashns/deep-learning-workbook","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aakashns%2Fdeep-learning-workbook","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aakashns%2Fdeep-learning-workbook/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aakashns%2Fdeep-learning-workbook/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aakashns%2Fdeep-learning-workbook/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aakashns","download_url":"https://codeload.github.com/aakashns/deep-learning-workbook/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aakashns%2Fdeep-learning-workbook/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30030829,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-03T00:31:48.536Z","status":"online","status_checked_at":"2026-03-03T02:00:07.650Z","response_time":61,"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","jupyter-notebook","keras","machine-learning","tensorflow"],"created_at":"2024-10-26T04:23:19.796Z","updated_at":"2026-03-03T02:31:43.374Z","avatar_url":"https://github.com/aakashns.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Learning Workbook\n\nThe Jupyter notebook [deep-learning-workbook.ipynb](./deep-learning-workbook.ipynb) outlines a universal blueprint that can be used to attack and solve any machine learning problem. It is based on the workflow described in the book [Deep Learning with Python](https://www.manning.com/books/deep-learning-with-python).\n\n## Usage Instructions\n\n1. Set up your dev environment with [Jupyter](http://jupyter.org/), [Tensorflow](https://www.tensorflow.org/) \u0026 [Keras](https://keras.io/) (or any other ML framework). Follow [this guide](https://blog.keras.io/running-jupyter-notebooks-on-gpu-on-aws-a-starter-guide.html) if you wish to use a GPU on AWS.\n\n2. Download the latest version of the workbook using the command:\n```bash\nwget https://raw.githubusercontent.com/aakashns/deep-learning-workbook/master/deep-learning-workbook.ipynb\n```\n\n3. Change the file name, title and kernel as desired. This notebook was originally written with the kernel `conda:tensorflow_p36` on the [AWS Deep Learning AMI](https://aws.amazon.com/marketplace/pp/B01M0AXXQB).\n\n4. Follow the steps described in to notebook, filling in the blanks marked as `TODO`.\n\n5. Once you're done building the final model, you can delete the cells containing instructions.\n\n## Deep Learning Workflow\n\nSee the Jupyter notebook [deep-learning-workbook.ipynb](./deep-learning-workbook.ipynb) for the detailed step-by-step workflow for solving machine learning problems using Deep Learning. Following is a short summary of the workflow:\n\n1. Define the problem at hand and the data you will be training on; collect the data or annotate it with labels.\n\n2. Choose how you will measure success on your problem. Which metrics will you be monitoring?\n\n3. Determine your evaluation protocol: hold-out validation? K-fold validation? Which portion of the data should you use for validation?\n\n4. Develop a first model that does better than a basic baseline: a model that has \"statistical power\".\n\n5. Develop a model that overfits.\n\n6. Regularize your model and tune its hyperparameters, based on performance on the validation data.\n\n## Credits\n\nThe Jupyter notebook is based on the universal workflow for machine learning outlined in the book [Deep Learning With Python](https://www.manning.com/books/deep-learning-with-python) by François Chollet, the author of [Keras](https://keras.io/). \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faakashns%2Fdeep-learning-workbook","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faakashns%2Fdeep-learning-workbook","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faakashns%2Fdeep-learning-workbook/lists"}