1. An Introduction
- Machine Learning and Neural Nets
2. The Perceptron learning procedure
- An overview of the main types of neural network architecture
3. The backpropagation learning procedure
- Learning the weights of a linear neuron
4. Learning feature vectors for words
- Learning to predict the next word
5. Object recognition with neural nets
- Why object recognition is difficult
6. Optimization: How to make the learning go faster
- What are the mini-batch gradient descent and adaptive learning rates
7. Recurrent neural networks
- About recurrent neural networks
8. More recurrent neural networks
9. Ways to make neural networks generalize better
- Building strategies to make neural networks generalize better
10. Combining multiple neural networks to improve generalization
- How to combine multiple neural networks to improve generalization
11. Hopfield nets and Boltzmann machines
12. Restricted Boltzmann machines (RBMs)
- About Boltzmann machine learning