Neural Networks Learning

# Machine Learning Notes(8)-Neural Networks Representation

## Neural Networks Model

- A single neuron model: logistic unit
- Takes 3+1 inputs(the extra input called bias is just like $\theta_0$ in logistic regression, not shown in picture).
- Both input and output could be represented as vectors, in which each unit has its own parameters $\theta$
- All the units in the same layer take the same input $\mathbf{x}$, as the pic shows.
- Each unit has only one output: $sigmoid(\theta^T x)$. Of course there’re other choices for sigmoid function.

- Neural Networks
- A neural network consists of an input Layer, an output layer and hidden layers.
- In the model above, layer 1 is input layer, 2 is hidden layer and 3 is the output layer.

# Machine Learning Notes(5)-Programming Exercise 1

Programming Exercise 1: Gradient Descent for Linear regression

# Machine Learning Notes(2)-A Linear Regression Example

This is my notes for the open course Machine Learning from coursera.

# Machine Learning Notes(1)-Supervised and Unsupervised Learning

This is my notes for the open course Machine Learning from coursera.