# π±Introduction

πͺ Beginning to solve problems of computer vision with Tensorflow and Keras

### π What is MNIST?

The MNIST database: (Modified National Institute of Standards and Technology database)

• π Fashion-MNIST is consisting of a training set of 60,000 examples and a test set of 10,000 examples

• π¨ Types:

• π’ MNIST: for handwritten digits

• π Fashion-MNIST: for fashion

• π Properties:

• π Grayscale

• 28x28 px

• 10 different categories

### π Important Terms

 Term Description β° Sequential That defines a SEQUENCE of layers in the neural network β Flatten Flatten just takes that square and turns it into a 1 dimensional set (used for input layer) π· Dense Adds a layer of neurons π₯ Activation Function A formula that introduces non-linear properties to our Network β¨ Relu An activation function by the rule: If X>0 return X, else return 0 π¨ Softmax An activation function that takes a set of values, and effectively picks the biggest one

The main purpose of activation function is to convert a input signal of a node in a NN to an output signal. That output signal now is used as a input in the next layer in the stack π₯

### π« Notes on performance

• Values in MNIST are between 0-255 but neural networks work better with normalized data, so we can divide every value by 255 so the values are between 0,1.

• There are multiple criterias to stop training process, we can specify number of epochs or a threshold or both

• Epochs: number of iterations

• Threshold: a threshold for accuracy or loss after each iteration

• Threshold with maximum number of epochs

We can check the accuracy at the end of each epoch by Callbacks π₯