 So a neural network is the network of artificial neurons. It tries to simulate our human brains and the neural network has many layers of the neurons. And the first layer we receive the input like image, video, sound, text, or anything, then the input data we go through all network layers and the output of one layer will be fed to the next layer. So there are many millions, there are millions of parameters in neural networks and the neural networks can be used to recognize things. For example, like neural networks can be used to recognize that there is a doll or there is a cat in the image. So there is a need to have big data in joining neural networks just like human, just like us. Actually, humans take advantage of big data. Imagine a person perceived like 30 frames, 30 images per second. That means 1800 images per minute and over 600 millions of images per year. So that's why we should give neural networks a similar opportunity to have the big data for the training. Yeah, so there are many, many applications of neural networks like facial recognition and driver's cars. So for example, like the faces detected by the smartphone's camera will be recognized by the neural network or in another application, the driver's car equipped with all the multiple cameras tried to recognize the surrounding environment. So the autonomous car are able to recognize other vehicles, recognize traffic signs, stop sign, and from the recognition the car can change the speed automatically and even doesn't break to avoid any potential accidents. So neural networks were invented a long time ago. Then it went through the long, long hibernation due to all the lightweight models because of the computational cost. So recently it grows again thanks to the advanced computational resources like Graphical Processing Unit, it's called GBU. So that's why now we see the prosperity of neural networks.