DigitRecognizer | correctly identify digits from a dataset tens

DigitRecognizer is a Jupyter Notebook library. DigitRecognizer has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.

MNIST ("Modified National Institute of Standards and Technology") is the de facto “hello world” dataset of computer vision. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike. The goal is to correctly identify digits from a dataset of tens of thousands of handwritten images. In my submission, I have implemented a neural network with 3 layers (input, hidden, output), from scratch. I tried to implement the concepts I learnt in ANdrew NG's course on Machine Learning. The Jupyter notebook contains all the necessary details for understanding my solution. My submission got a score of 90% on Kaggle.