Quantum mechanics

Cellular neural network

Backpropagation

Computer security

Computer graphics (images)

Power (physics)

Computer science

Physics

Rectification

Pattern recognition (psychology)

Mathematics

Block (permutation group theory)

Artificial intelligence

Geometry

Cluster analysis

Point (geometry)

Deep learning

Artificial neural network

Convolutional neural network

Speech recognition

Computer vision

Key (lock)

IEEE Signal Processing Magazine

There is a resurging interest in developing a neural-network-based solution to the supervised machine-learning problem. The convolutional neural network (CNN) will be studied in this lecture note. We introduce a rectified-correlations on a sphere (RECOS) [1] transform as a basic building block of CNNs. It consists of two main concepts: 1) data clustering on a sphere and 2) rectification. We then interpret a CNN as a network that implements the guided multilayer RECOS transform with two highlights. First, we compare the traditional single-layer and modern multilayer signal-analysis approaches, point out key areas that enable the multilayer approach, and provide a full explanation to the operating principle of CNNs. Second, we discuss how guidance is provided by labels through backpropagation (BP) in the training.

The CNN as a Guided Multilayer RECOS Transform [Lecture Notes]