This notebook is easier to read on Kaggle.
Please click here to view this notebook on Kaggle. I'd love to receive comments and suggestions over there too.
This is my first time working on a computer vision project and developing a neural network!
In order to start with computer vision, I'm using Kaggle's Digit Recognizer competition to put on practice the knowledge I've acquired after studying the principles of computer vision and deep learning.
The MNIST ("Modified National Institute of Standards and Technology") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike.
The goal of this competition is to take images of handwritten digits and create a machine learning model that can correctly identify what digit is in the image. The metrics used to evaluate how well the model performs is the accuracy of predicitions, that is the percentage of images that our model can label correctly.
According to this IBM article, convolutional neural networks are distinguished from other neural networks by their superior performance with image, speech and audio inputs, which makes it ideal for a getting started project working with image classification.
- Pandas
- Numpy
- Plotly Express
- Matplotlib.pyplot
- Tensorflow
- Keras
- Sklearn
Luís Fernando Torres