{ "id": 271592, "title": "[Beginners start here] Good Baseline solutions", "url": "/competitions/digit-recognizer/discussion/271592", "author_name": "KritiDoneria", "post_date": "2021-09-11T11:12:10.158000", "votes": 2, "comment_count": 0, "views": null, "content": "
    \n

  1. A simple K Nearest Neighbours + CNN approach by @ahmed121ashraf131

    2. \n

  2. Data augmentation and transfer learning approach by @pybear

    3. \n

  3. Simple MNIST numpy from scratch by @scaomath

    4. \n

  4. Catboost approach by @onnieqin

    5. \n

  5. Deep Convolutional Generative Adversarial Network by @alyeasin

    6. \n
\n

If you just read through these notebooks, you'll learn a lot.
\nPlease upvote the original notebooks if you like their work

", "messages": [ { "id": 1509512, "postDate": "2021-09-11T11:12:10.157Z", "content": "
    \n

  1. A simple K Nearest Neighbours + CNN approach by @ahmed121ashraf131

    2. \n

  2. Data augmentation and transfer learning approach by @pybear

    3. \n

  3. Simple MNIST numpy from scratch by @scaomath

    4. \n

  4. Catboost approach by @onnieqin

    5. \n

  5. Deep Convolutional Generative Adversarial Network by @alyeasin

    6. \n
\n

If you just read through these notebooks, you'll learn a lot.
\nPlease upvote the original notebooks if you like their work

", "rawMarkdown": "1. [A simple K Nearest Neighbours + CNN approach](https://www.kaggle.com/ahmed121ashraf131/mnist-simple-cnn-knn-accuracy-100-top-1) by @ahmed121ashraf131\n\n2. [Data augmentation and transfer learning approach ](https://www.kaggle.com/pybear/cnn-100-transfer-learning-data-augmentation) by @pybear\n\n3. [Simple MNIST numpy from scratch](https://www.kaggle.com/scaomath/simple-mnist-numpy-from-scratch) by @scaomath\n\n4. [Catboost approach](https://www.kaggle.com/lonnieqin/catboost-mnist-classification) by @onnieqin\n\n5. [Deep Convolutional Generative Adversarial Network](https://www.kaggle.com/alyeasin/deep-convolutional-generative-adversarial-network) by @alyeasin\n\n\nIf you just read through these notebooks, you'll learn a lot.\nPlease upvote the original notebooks if you like their work", "votes": 2 } ], "comments": [], "raw_markdown_by_id": { "1509512": "1. [A simple K Nearest Neighbours + CNN approach](https://www.kaggle.com/ahmed121ashraf131/mnist-simple-cnn-knn-accuracy-100-top-1) by @ahmed121ashraf131\n\n2. [Data augmentation and transfer learning approach ](https://www.kaggle.com/pybear/cnn-100-transfer-learning-data-augmentation) by @pybear\n\n3. [Simple MNIST numpy from scratch](https://www.kaggle.com/scaomath/simple-mnist-numpy-from-scratch) by @scaomath\n\n4. [Catboost approach](https://www.kaggle.com/lonnieqin/catboost-mnist-classification) by @onnieqin\n\n5. [Deep Convolutional Generative Adversarial Network](https://www.kaggle.com/alyeasin/deep-convolutional-generative-adversarial-network) by @alyeasin\n\n\nIf you just read through these notebooks, you'll learn a lot.\nPlease upvote the original notebooks if you like their work" } }