Neural networks, also known as artificial neural networks (ANNs), are at the core of deep learning algorithms. Their structures are inspired by the way human brain works. Because neural networks are so powerful, the tools can be used to solve a number of problems in different fields, including but not limited to reinforcement learning, computer vision, NLP, etc.
MNIST is a large database of handwritten digits that is commonly used for training various image processing systems. With the MNIST dataset, we can use Pytorch to create a simple fully connected ANNs to classify handwritten digets with high accuracy.
- The definition of ANN and how it works
- Using Pytorch to create a fully connected neural networks and use it to solve a classification problem