1. Non-linear hypotheses
- why introduce non-linear hypotheses?
- high dimensional data
- non-linear hypotheses
2. Neurons and the brain
- Neural networks
- origins: algorithms that try to mimic the brain
- was very widely used in 80s and early 90s, popularity diminished in late 90s
- recent resurgence: state-of-the-art technique for many applications
3. Model representation I
- neuron model: logistic unit
- sigmoid (logistic) activation function
4. Model representation II
- forward propagation: vectorized implementation
5. Examples and intuitions I
AND and OR function
6. Examples and intuitions II
XNOR
7. Multi-class classification
number of classes = number of output units
Reference: http://blog.csdn.net/abcjennifer/article/details/7749309#reply