Deep Learning noun interpretation

Feedforward Neural Networks : The simplest neural network in which each neuron receives the full connection input from the previous layer and outputs it to the next layer, without feedback from the entire process.

bp neural network : Error back propagation algorithm (error back propagation Training), referred to as BP, the system solves the problem of multi-layered neural network hidden layer connection right learning, and trains the multilayer Feedforward neural network according to the training method of error forward propagation.

gradient descent algorithm : Used to find the minimum value, the opposite direction of the gradient is the fastest direction of the function value descent speed, we believe that the fastest direction along the function to find the minimum value faster.

Deep Learning: Deep Learning (learning) is a new area of machine learning that is motivated by the creation and simulation of a neural network that mimics the human brain's mechanisms for interpreting data, examples, sounds, and texts. Deep learning is a kind of unsupervised learning.

single-Layer perceptron : (PLA) The idea of a single-layer perceptron is to mimic the way a single neuron in the brain works: activation or not. The perceptron receives multiple input signals and outputs a signal if the input signal exceeds a certain threshold, otherwise it does nothing.

Multilayer perceptron : (MPL) multilayer neural networks, which contain hidden layers.

Deep Learning noun interpretation