Neural Network 神經網絡
Some basic knowledge are required to better understand what is Neural Network.
- Linear Regression
- Sigmoid Squashing Function
- Rectified linear unit
- Derivation
- Error
Two important types of artificial neuron
- perceptron neuron
- sigmoid neuron
Perceptron Neuron
- Detemine output with Weight and Bias
- Each perceptron has only one output
- input x usually zero or one
- output = wx + b
- w = weight
- b = bias
Sigmoid Neuron
- Detemine output with Weight and Bias, plus sigmoid σσ
- Each perceptron has only one output
- input x between zero or one
- output = σ (wx + b)
- w = weight
- b = bias
- σ =sigmoid
- sigmoid function: σz = 1+ (1 / 1 + e^(-z))
- Or , output = 1 / 1 + exp (−∑jwjxj−b)
Reference:
https://brohrer.github.io/how_neural_networks_work.html
http://www.neuralnetworksanddeeplearning.com
Feedforward Neural Network : neural networks where the output from one layer is used as input to the next layer. There are no loops in the network - information is always fed forward, never fed back.
Recurrent Neural Network: Neural networks where the output from one layer is used as input to the next layer with loops in a limited duration of time in the network.
http://www.neuralnetworksanddeeplearning.com
Architecture of Neural Network
Feedforward Neural Network : neural networks where the output from one layer is used as input to the next layer. There are no loops in the network - information is always fed forward, never fed back.
Recurrent Neural Network: Neural networks where the output from one layer is used as input to the next layer with loops in a limited duration of time in the network.
CNN - Convolutional Neural Network 卷積神經網絡
CNN is about space?
RNN - Recurrent Neural Network
RNN is about time?
