Neural Network has a collection of artificial neurons arranged in a sequence of layers, each of which links to other layers. The input units are intended to obtain different forms of information from the external world that the network attempts to learn from, recognize, or otherwise process. The output units sit on the opposite side of the network and signal how it responds to the information it has learned. One or more layers of hidden unit form the artificial brain. The edges are associated with a weight; more the weight, the more influence it has on the output. Every unit sums up the inputs it takes in and if the result exceeds a certain threshold value, the unit "fires" and activates the units it's associated with.
Goals:Learning without programming, computation in parallel, finding network parameters automatically.
BrandIdea’s Implementation:SKU Recommendation System: RESKUR