Secret Behind the PRISMA app !

Recently a organization called PRISMA - AI has released an app for IOS with some amaing photo editing features. They simply cartoon for your photo with good accuracy. It has recoreded its highest download count recently. 

So how it works ? Simply prisma works according to a Neural Network. A neural network is an mathematical implement of neurons.

How the Human Brain Learns?

Much is still unknown about how the brain trains itself to process information, so theories abound. In the human brain, a typical neuron collects signals from others through a host of fine structures called dendrites. The neuron sends out spikes of electrical activity through a long, thin stand known as an axon, which splits into thousands of branches. At the end of each branch, a structure called a synapse converts the activity from the axon into electrical effects that inhibit or excite activity from the axon into electrical effects that inhibit or excite activity in the connected neurones. When a neuron receives excitatory input that is sufficiently large compared with its inhibitory input, it sends a spike of electrical activity down its axon. Learning occurs by changing the effectiveness of the synapses so that the influence of one neuron on another changes.

                                                                 Components of a neuron

                                                                          The synapse

An Artificial Neuron

An artificial neuron is a device with many inputs and one output. The neuron has two modes of operation; the training mode and the using mode. In the training mode, the neuron can be trained to fire (or not), for particular input patterns. In the using mode, when a taught input pattern is detected at the input, its associated output becomes the current output. If the input pattern does not belong in the taught list of input patterns, the firing rule is used to determine whether to fire or not.

Also there are more about firing rules and other theoretical stuffs, but this is the basic idea of a neuron. 

Lets come back to the app again, This app has a neural network as above with some functions. as an example, there will be a function like " if these are the RGB values of this area of the photo, use this effect". Also the NN network is learning himself with new patterns in every use. So when time passes it comes more accurate! Also when the NN gets overloaded, the app says try again later! Recently TESLA motors also started to use NN for their self driving concept.