Quantum Neural Network

1015 Words3 Pages

Chapter 1

Quantum Neural Network

1.1 Introduction and Background

The eld of arti cial neural networks (ANNs) draws its inspiration from the

working of human brain and the way brain processes information. An ANN

is a directed graph with highly interconnected nodes called neurons.Each

edge of the graph has a weight associated with it to model the synaptic

eciency. The training process involves updating the weights of the network

in such a way that the network learns to solve the problem.

The neurons in the network work together to solve speci c problems.

The network can be trained to do various tasks like pattern recognition,

data classi cation,function approximation etc. ANNs are widely used in the

elds of computer vision and speech recognition.

1.1.1 Architecture of an Arti cial Neural Network

1.1.2 Backpropagation

Learning is the way we acquire knowledge about the world around us, and it

is through this process of knowledge acquisition, that the environment alters

our behavioural responses. Similarly, in arti cial neural networks, learning

rules are used, to modify the behaviour of the network in response to the

external stimuli (inputs).

For multilayered feedforward networks, a commonly used algorithm for

weight adjustment is the backpropagation algorithm. There is some math

1

2 CHAPTER 1. QUANTUM NEURAL NETWORK

Figure 1.1: feedforward multilayer ANN

involved in the derivation of the formula which can be referred to from [4].

The nal form of the formula looks like:

wij = jyi

Where,

wij is the weight between the neurons i; j

j is the local gradient of the jth neuron

and, yi is the output of the ithneuron

1.2 Quantum Mechanics and ANN

There are problems that are computationally hard i.e. ...

... middle of paper ...

..., which are discussed in detail in [5].

1.3.3 Training and Performance

The training of the network can be carried out using the backpropagation

algorithm. Because of the unavailability of quantum hardware, the network

cannot be tested but we can simulate the network on a classical computer.

1.4 Summary and Discussion

Provide a summary and discuss what you have understood. summarize the

main points and also mention if have found some subtopics dicult.

Bibliography

[1] A. Narayanan, T. Menneer, Information Sciences 128 (2000) 231-255

[2]

[3] H. Everett, Relative state formulation of quantum mechanics, Reviews

of Modern Physics 29 (1957) 454-462.

[4] Satish Kumar, Neural Networks: A Classroom Approach

[5] T.S.I. Menneer, Quantum arti cial neural networks, Ph.D. Thesis, De-

partment of Computer Science, University of Exeter, Exeter, EX4 4PT,

UK, 1998

7

Open Document