An optical neural network is a physical implementation of an artificial neural network

Artificial neural network

An artificial neural network , usually called neural network , is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks. A neural network consists of an interconnected group of artificial neurons, and it processes...

  with optical components

Photonics

The science of photonics includes the generation, emission, transmission, modulation, signal processing, switching, amplification, detection and sensing of light. The term photonics thereby emphasizes that photons are neither particles nor waves — they are different in that they have both particle...

.

Some artificial neural networks that have been implemented as optical neural networks include the Hopfield neural networkhttp://www.opticsinfobase.org/abstract.cfm?id=78568http://nr.stic.gov.tw/ejournal/ProceedingA/v24n1/73-78.pdf and the Kohonen self-organizing map

Self-organizing map

A self-organizing map or self-organizing feature map is a type of artificial neural network that is trained using unsupervised learning to produce a low-dimensional , discretized representation of the input space of the training samples, called a map...

 with liquid crystal

Liquid crystal

Liquid crystals are a state of matter that have properties between those of a conventional liquid and those of a solid crystal. For instance, an LC may flow like a liquid, but its molecules may be oriented in a crystal-like way. There are many different types of LC phases, which can be...

s http://link.aip.org/link/?PSISDG/1296/378/1.

Biological neural network

Biological neural network

In neuroscience, a biological neural network describes a population of physically interconnected neurons or a group of disparate neurons whose inputs or signalling targets define a recognizable circuit. Communication between neurons often involves an electrochemical process...

s function on an electrochemical basis, while optical neural networks use electromagnetic waves. Optical interfaces to biological neural network

Biological neural network

In neuroscience, a biological neural network describes a population of physically interconnected neurons or a group of disparate neurons whose inputs or signalling targets define a recognizable circuit. Communication between neurons often involves an electrochemical process...

s can be created with optogenetics

Optogenetics

Optogenetics is the combination of genetic and optical methods to control specific events in targeted cells of living tissue, even within freely moving mammals and other animals, with the temporal precision needed to keep pace with functioning intact biological systems.In 2010, optogenetics was...

, but is not the same as an optical neural networks. In biological neural networks there exist a lot of different mechanisms for dynamically changing the state of the neurons, these include short-term and long-term synaptic plasticity

Synaptic plasticity

In neuroscience, synaptic plasticity is the ability of the connection, or synapse, between two neurons to change in strength in response to either use or disuse of transmission over synaptic pathways. Plastic change also results from the alteration of the number of receptors located on a synapse...

. Synaptic plasticity is among the electrophysiological phenomena used to control the efficiency of synaptic transmission, long-term for learning and memory, and short-term for short transient changes in synaptic transmission efficiency. Implementing this with optical components is difficult, and ideally requires advanced photonic materials. Properties that might be desirable in photonic materials for optical neural networks include the ability to change their efficiency of transmitting light, based on the intensity of incoming light.

There is one recent (2007) model of Optical Neural Network: the Programmable Optical Array/Analogic Computer (POAC). It had been implemented in the year 2000 and reported based on modified Joint Fourier Transform Correlator (JTC) and Bacteriorhodopsin (BR) as a holographic optical memory. Full parallelism, large array size and the speed of light are three promises offered by POAC to implement an optical CNN. They had been investigated during the last years with their practical limitations and considerations yielding the design of the first portable POAC version.

The practical details: hardware (optical setups) and software (optical templates) are published. However, POAC is a general purpose and programmable array computer that has a wide range of applications including:

• image processing
  Image processing
  In electrical engineering and computer science, image processing is any form of signal processing for which the input is an image, such as a photograph or video frame; the output of image processing may be either an image or, a set of characteristics or parameters related to the image...
  
  
• pattern recognition
  Pattern recognition
  In machine learning, pattern recognition is the assignment of some sort of output value to a given input value , according to some specific algorithm. An example of pattern recognition is classification, which attempts to assign each input value to one of a given set of classes...
  
  
• target tracking
• real-time video processing
• document security
• optical switching

External links

• Optical Computing Group, Analogic and Neural Systems Laboratory, Computer and Automation Research Institute, Hungarian Academy of Sciences: http://lab.analogic.sztaki.hu
• Institute for optical neural technologies (Russian Academy of Sciences): http://correct web address required