AI人工智能神精网络专题扩展阅读材料/RNN/LSTM-香港科技大学博士研究专题扩展阅读材料

1．        Long Short-Term Memory Networks With Python
Author(s): Jason Brownlee
Description: This book was born out of one thought:
If I had to get a machine learning practitioner proficient with LSTMs in two weeks (e.g. capable of applying LSTMs to their own sequence prediction projects), what would I teach?
I had been researching and applying LSTMs for some time and wanted to write something on
the topic, but struggled for months on how exactly to present it. The above question crystallized
it for me and this whole book came together.
The above motivating question for this book is clarifying. It means that the lessons that I teach are focused only on the topics that you need to know in order to understand (1) what LSTMs are, (2) why we need LSTMs and (3) how to develop LSTM
2．        Nonlinear Real-Time Emulation of a Tube Amplifier with a Long Short Term Memory Neural-Network
Author(s): Schmitz Thomas
Description: Numerous audio systems for musicians are expensive and bulky. Therefore, it could be advantageous to model
them and to replace them by computer emulation. Their nonlinear behavior requires the use of complex models.
We propose to take advantage of the progress made in the field of machine learning to build a new model for such
nonlinear audio devices (such as the tube amplifier). This paper specially focuses on the real-time constraints of the
model. Modifying the structure of the Long Short Term Memory neural-network has led to a model 10 times faster
while keeping a very good accuracy. Indeed, the root mean square error between the signal coming from the tube
amplifier and the output of the neural network is around 2%.
3．        Interactions Between Short-Term and Long-Term Memory in the Verbal Domain
Author(s): Annabel Thorn
Description:The relationship between short-term and long-term memory systems is an issue of central concern to memory theorists. The association between temporary memory mechanisms and established knowledge bases is now regarded as critical to the development of theoretical and computational accounts of verbal short-term memory functioning. However, to date there is no single publication that provides dedicated and full coverage of current understanding of the association between short-term and long-term memory systems.
Interactions between Short-Term and Long-Term Memory in the Verbal Domain is the first volume to comprehensively address this key issue. The book, focusing specifically on memory for verbal information, comprises chapters covering current theoretical approaches, together with the very latest experimental work, from leading researchers in the field. Chapters contributed to the book draw on both cognitive and neuropsychological research and reflect both conceptual and computational approaches to theorising. The contributing authors represent current research perspectives from both sides of the Atlantic.
By addressing this important topic head-on, Interactions between Short-Term and Long-Term Memory in the Verbal Domain represents an invaluable resource for academics and students alike.