Figuring out if you win or lose

Using the Loss function

Training a neural

network

It only returns x if x is greater than zero

For a value x, it returns 1/x

It only returns x if x is less than zero

It returns the negative of x

Makes them sharper

Reduces information in them while maintaining some features

Isolates features in them

Combines them

To test a network with previously unseen data

To make training quicker

To train a network with previously unseen data

To make testing quicker

False

True

An amount of mass occupying a volume

A layer of connected

neurons

A single neuron

A layer of disconnected neurons

1. There's not enough information to answer that question

1. The 10th element on the list is the biggest, and the ankle boot is labelled 9

1. The ankle boot is label 9, and there are 0->9 elements in the list

There are 10 different labels

Purely arbitrary

To make it classify 10x faster

To make it train 10x faster

1. It's 10 random meaningless values

1. It's the probability that this item is each of the 10 classes

1. It's the first 10 classifications that the computer made

82x82 Greyscale

28x28 Color

28x28 Greyscale

100x100 Color