Untitled

Abstract

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 self-organizing 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 the next day with an error rate of 47.1%. The error rate reduces to around 40% when rejecting examples where the system has low confidence in its prediction. We show that the symbolic representation aids the extraction of symbolic knowledge from the trained recurrent neural networks in the form of deterministic finite state automata. These automata explain the operation of the system and are often relatively simple. Automata rules related to well known behavior such as trend following and mean reversal are extracted.

A Brief Survey of Telerobotic Time Delay Mitigation

“…In this section, we examine various neural network-based methods. Prediction of individual sequences in terms of time or time series prediction is challenging and at the same time an important area of study in machine learning (Giles et al, 2001;Anava et al, 2013Anava et al, , 2015Ak et al, 2015;Fang et al, 2017Fang et al, , 2020. Extracting good representative pairs of input and output data is essential in machine learning algorithms.…”

“…Connor et al (1994) proposed a robust learning algorithm based on filtering anomalies from the data and used this filtered data for estimating parameters and do forecasting. In Giles et al (2001), they examine the difficulties of RNNs for forecasting nonstationary and noisy data, and they introduced a pre-processing method to overcome these problems. However, when the gap between the relevant information and the prediction is large, RNNs become very slow and, in some cases, are unable to learn the long-term dependencies (Bengio et al, 1994).…”

Forecasting spot prices of agricultural commodities in India: Application of deep‐learning models

“…Interestingly, to our knowledge, there has been no attempt to deploy LSTM models previously on Indian agricultural commodity exchanges to predict the spot market prices. However, LSTM has been used to predict the volatility of the S&P 500 (Xiong, Nichols, & Shen, 2015) and to forecast foreign exchange rates (Giles, Lawrence, & Tsoi, 2001). Nikou, Mansourfar, and Bagherzadeh (2019) predicted the daily close price data of a UK exchange-traded fund from January 2015 to June 2018 using four models of machine learning and indicated that the deep-learning method was better in prediction than the other methods.…”

Machine learning of two-dimensional spectroscopic data

“…(7). To find the optimal network configuration [44] we vary the parameters in the training, including the number of hidden layers M, the dimension of a single hidden layer N h , the number of training data N, the number of epochs and the batch size B. We did not find significant improvements in the accuracy when increasing the number of layers in the network M nor increasing the number of training data N. We calculated the MSE as a function of the dimension of the hidden layer N h and observe slight decrease with increasing N h .…”