Neural Networks Presentation - Annotated bibliography

[1] Buckland, Mat. 2002. AI Techniques For Game Programming: Premier Press.

The author provides an explanation of neural networks in simple terms from the point of view of an artificial intelligence programmer. An explanation of backpropagation is also included, and sample code is provided at every step.

[2] Karaali, O., G. Corrigan, N. Massey, C. Miller, O. Schnurr, and A. Mackie. 1998. A high quality text-to-speech system composed of multiple neural networks. Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing 2:1237-40. Link

The authors, Motorola employees, describe a text-to-speech conversion system using neural networks for both linguistics and speech processing. Dynamic programming is combined with neural networks. The system is said to be expected to adapt to new languages better than other methods.

[3] Marmanis, H., and D. Babenko. 2009. Algorithms of the Intelligent Web: Manning Publications.

The authors include an example of a fraud detection system using neural networks, with sample code. A brief overview of neural networks is also provided.

[4] Marolt, M. 2001. Transcription of polyphonic piano music with neural networks. Proceedings of the 10th Mediterranean Electrotechnical Conference, 2000. MELECON 2000. 2:512-5. Link

The author describes the use of neural networks for the transcription of piano music. 88 artificial neural networks are used for the identification of as many notes. The errors of the system are identified and explained.

[5] Murray, J. C., H. R. Erwin, and S. Wermter. 2009. Robotic sound-source localisation architecture using cross-correlation and recurrent neural networks. Neural Networks 22 (2):173-89. Link

The authors describe the use of a feedback-enabled artificial neural network. The system has 76 inputs and 76 outputs, and is meant to track the movement of a sound source.

[6] Rho, S., B. Han, E. Hwang, and M. Kim. 2007. MUSEMBLE: A Music Retrieval System Based on Learning Environment. Proceedings of the 2007 IEEE International Conference on Multimedia and Expo:1463-6. Link

The authors explain the use of a feed-forward artificial neural network linked to a genetic algorithm. The genetic algorithm feeds pitch and duration segments to the neural network. The results describe the minimization of input data.