What is a neural network?
Example: housing price prediciton.
Each neuron: ReLU function
Stacking multiple layers of neurons: hidden layers are concepts more general than input layer — found automatically by NN.
Supervised Learning with Neural Networks
supervised learning: during training, always have output corresponding to input.
Different NN types are used for different problems:
structured data: database, each feature/column has a well-defined meaning. unstructured data: audio/image/text, no well-defined meaning for pixels/tokens
Why is Deep Learning taking off?
scale drives deep learning progress. (scale: both of NN and of data)
trandition methods: pleateaus as amount of data grows further.
NN: grows with data.
- data scales up
- computation faster
- new algorithms, e.g. from sigmoid to ReLU, which in turn speeds up computation too.
About this course
This course: implementing NN.
Part 1 of series «Andrew Ng Deep Learning MOOC»：
- [Neural Networks and Deep Learning] week1. Introduction to deep learning
- [Neural Networks and Deep Learning] week2. Neural Networks Basics
- [Neural Networks and Deep Learning] week3. Shallow Neural Network
- [Neural Networks and Deep Learning] week4. Deep Neural Network
- [Improving Deep Neural Networks] week1. Practical aspects of Deep Learning
- [Improving Deep Neural Networks] week2. Optimization algorithms
- [Improving Deep Neural Networks] week3. Hyperparameter tuning, Batch Normalization and Programming Frameworks
- [Structuring Machine Learning Projects] week1. ML Strategy (1)
- [Structuring Machine Learning Projects] week2. ML Strategy (2)
- [Convolutional Neural Networks] week1. Foundations of Convolutional Neural Networks
- [Convolutional Neural Networks] week2. Deep convolutional models: case studies
- [Convolutional Neural Networks] week3. Object detection
- [Convolutional Neural Networks] week4. Special applications: Face recognition & Neural style transfer
- [Sequential Models] week1. Recurrent Neural Networks
- [Sequential Models] week2. Natural Language Processing & Word Embeddings
- [Sequential Models] week3. Sequence models & Attention mechanism