What is deep learning?
According to wikipedia 1
Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using model architectures, with complex structures or otherwise, composed of multiple non-linear transformations.
Deep learning is part of a broader family of machine learning methods based on learning representations of data.
An observation (e.g., an image) can be represented in many ways such as a vector of intensity values per pixel, or in a more abstract way as a set of edges, regions of particular shape, etc.. Some representations make it easier to learn tasks (e.g., face recognition or facial expression recognition) from examples.
One of the promises of deep learning is replacing handcrafted features with efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction.
Traditional Model vs Deep Learning
In traditional models, we must extract features by hand, after that we train these features with some classifiers
With deep learning, we can learn representation of objects as well as its classifiers.
Hierarchy of representations with increasing level of abstraction. Each stage is a kind of trainable feature transform.
pixel > edge > texton > motif > part > object
character > word > word group > clause > sentence > story
sample > spectral band > sound > … > phone > phoneme > word
Demos and Applications
Yann Lecun with ImageNetOnline Learning Demo in his deep learning class 2. This program auto learn new object when he pointed camera to it
Voice recognition systems like Apple Siri, Google Now and Windows Cortana all use deep learning 3
Facebook’s DeepFace Software Can Match Faces With 97.25% Accuracy 4
- Introduction about Deep Learning, http://colah.github.io/