Noisy Time Series Prediction using a Recurrent Neural Network and Grammatical Inference

Noisy Time Series Prediction using a Recurrent Neural Network and Grammatical Inference (2001)

Cached

Download Links

by C. Lee Giles , Steve Lawrence , A. C. Tsoi

Venue:	Machine Learning
Citations:	40 - 0 self

BibTeX

@INPROCEEDINGS{Giles01noisytime,
    author = {C. Lee Giles and Steve Lawrence and A. C. Tsoi},
    title = {Noisy Time Series Prediction using a Recurrent Neural Network and Grammatical Inference},
    booktitle = {Machine Learning},
    year = {2001},
    pages = {161--183}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

Financial forecasting is an example of a signal processing problem which is challenging due to small sample sizes, high noise, non-stationarity, and non-linearity. Neural networks have been very successful in a number of signal processing applications. We discuss fundamental limitations and inherent difficulties when using neural networks for the processing of high noise, small sample size signals. We introduce a new intelligent signal processing method which addresses the difficulties. The method proposed uses conversion into a symbolic representation with a selforganizing map, and grammatical inference with recurrent neural networks. We apply the method to the prediction of daily foreign exchange rates, addressing difficulties with non-stationarity, overfitting, and unequal a priori class probabilities, and we find significant predictability in comprehensive experiments covering 5 different foreign exchange rates. The method correctly predicts the direction of change for th...

Citations

3377	Introduction to Automata Theory, Languages, and Computation - Hopcroft, Motwani, et al. - 2003
2726	The self-organizing map - Kohonen - 1990
2716	Neural networks: A comprehensive foundation - Haykin - 1994
439	Efficient Capital Markets: A Review of Theory and Empirical Work - Fama - 1970
382	The behavior of stock-market prices - Fama - 1965
375	Factorial hidden markov models - Ghahramani, Jordan - 1997
361	Detecting strange attractors in turbulence - Takens - 1981
313	Universal approximation bounds for superpositions of a sigmoidal function - Barron - 1993
251	Distributed representations, simple recurrent networks, and grammatical structure - Elman - 1991
209	Modelling financial time series - Taylor - 1986
191	Adaptive Control Processes - Bellman - 1961
176	Extracting refined rules from knowledge-based neural networks - Towell, Shavlik - 1993
163	Learning and extracted finite state automata with second-order recurrent neural networks. Neural Comput - Giles, Miller, et al. - 1992
139	On the computational power of neural nets - Siegelmann, ED - 1995
135	Forecasting Economic Time Series - Granger, Newbold - 1986
132	Finite state automata and simple recurrent networks - Cleeremans, Servan-Schreiber, et al.
95	A Random Walk Down Wall - Malkiel - 1990
82	Learning from Hints in Neural Networks - Abu–Mostafa - 1990
82	Induction of finite-state languages using second-order recurrent networks - Watrous, Kuhn - 1992
71	Hopfield; Large automatic learning, rule extraction and generalization - Denker, Schwartz, et al. - 1987
66	The Truth Will Come to Light: Directions and Challenges in Extracting the Knowledge Embedded Within Trained Artificial Neural Networks - Tickle, Andrews, et al. - 1998
65	FIR and IIR synapses, a new neural network architecture for time-series modeling - Back, Tsoi - 1991
63	Nonlinear prediction of chaotic time series using support vector machines - Mukherjee, Osuna, et al. - 1997
61	An overview of predictive learning and function approximation - Friedman - 1994
60	Predicting Sunspots and Exchange Rates with Connectionist Networks - Weigend, Rumelhart, et al. - 1991
57	Extraction of rules from discrete-time recurrent neural networks - Omlin, Giles - 1996
54	On the representation of continuous functions of several variables by superposition of continuous functions of one variable and addition - Kolmogorov - 1957
54	On a method of investigating periodicities in disturbed series, with special reference to Wölfer’s sunspot - Yule - 1927
51	Neural Networks for Speech and Sequence Recognition - Bengio - 1996
40	Natural Language Grammatical Inference with Recurrent Neural Networks - Lawrence, Giles, et al. - 2000
39	Note on learning rate schedules for stochastic optimization - Darken, Moody - 1991
39	Higher order recurrent networks and grammatical inference - Giles, Sun, et al. - 1990
39	neural expert system with automated extraction of fuzzy if-then rules - Hayashi, “A - 1991
39	Statistical mechanics of nonlinear nonequilibrium financial markets - Ingber - 1984
39	Symbolic representation of neural networks - Setiono, Liu - 1996
37	Extracting and learning an unknown grammar with recurrent neural networks - Giles, Miller, et al. - 1992
37	Rule-based Machine Learning Methods for Functional Prediction - Weiss, Indurkhya - 1995
36	Dynamic construction of finite-state automata from examples using hill-climbing - Tomita - 1982
32	A non-random walk down Wall Street - Lo, MacKinlay - 2001
30	Rule induction through integrated symbolic and subsymbolic processing - McMillan, Mozer, et al. - 1992
29	Efficient Market Hypothesis - Malkiel - 1989
29	Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks - Saad, Prokhorov, et al. - 1998
28	Kolmogorov’s Theorem Is Relevant - Kurkova
26	Template-based algorithms for connectionist rule extraction - Alexander, Mozer - 1995
25	The extraction of refined rules from knowledge based neural networks - Towell, Shavlik - 1993
24	Communication and Networking for - JORDAN, CHURCmLL - 1990
23	Time-series segmentation using predictive modular neural networks - Kehagias, Petridis - 1997
20	Learning a class of large finite state machines with a recurrent neural network. Neural Networks - Giles, Lawrence, et al. - 1995
19	Induction of Finite State Languages Using Second-Order Recurrent Networks - Watrous - 1992
19	Discrete recurrent neural networks for grammatical inference - Zeng, Goodman, et al. - 1994