Modeling Financial Time Series with Artificial Neural Networks

Financial time series convey the decisions and actions of a population of human actors over time. Econometric and regressive models have been developed in the past decades for analyzing these time series. More recently, biologically inspired artificial neural network models have been shown to overcome some of the main challenges of traditional techniques by better exploiting the non-linear, non-stationary, and oscillatory nature of noisy, chaotic human interactions. This review paper explores the options, benefits, and weaknesses of the various forms of artificial neural networks as compared with regression techniques in the field of financial time series analysis.

The Construction of Arbitrary Stable Dynamics in Non-Linear Neural Networks

In this paper, two methods for constructing systems of ordinary differential equations realizing any fixed finite set of equilibria in any fixed finite dimension are introduced; no spurious equilibria are possible for either method. By using the first method, one can construct a system with the fewest number of equilibria, given a fixed set of attractors. Using a strict Lyapunov function for each of these differential equations, a large class of systems with the same set of equilibria is constructed. A method of fitting these nonlinear systems to trajectories is proposed. In addition, a general method which will produce an arbitrary number of periodic orbits of shapes of arbitrary complexity is also discussed. A more general second method is given to construct a differential equation which converges to a fixed given finite set of equilibria. This technique is much more general in that it allows this set of equilibria to have any of a large class of indices which are consistent with the Morse Inequalities. It is clear that this class is not universal, because there is a large class of additional vector fields with convergent dynamics which cannot be constructed by the above method. The easiest way to see this is to enumerate the set of Morse indices which can be obtained by the above method and compare this class with the class of Morse indices of arbitrary differential equations with convergent dynamics. The former set of indices are a proper subclass of the latter, therefore, the above construction cannot be universal. In general, it is a difficult open problem to construct a specific example of a differential equation with a given fixed set of equilibria, permissible Morse indices, and permissible connections between stable and unstable manifolds. A strict Lyapunov function is given for this second case as well. This strict Lyapunov function as above enables construction of a large class of examples consistent with these more complicated dynamics and indices. The determination of all the basins of attraction in the general case for these systems is also difficult and open.

Genetically Generated Neural Networks I: Representational Effects

This paper studies several applications of genetic algorithms (GAs) within the neural networks field. After generating a robust GA engine, the system was used to generate neural network circuit architectures. This was accomplished by using the GA to determine the weights in a fully interconnected network. The importance of the internal genetic representation was shown by testing different approaches. The effects in speed of optimization of varying the constraints imposed upon the desired network were also studied. It was observed that relatively loose constraints provided results comparable to a fully constrained system. The type of neural network circuits generated were recurrent competitive fields as described by Grossberg (1982).

Genetically Generated Neural Networks II: Searching for an Optimal Representation

Genetic Algorithms (GAs) make use of an internal representation of a given system in order to perform optimization functions. The actual structural layout of this representation, called a genome, has a crucial impact on the outcome of the optimization process. The purpose of this paper is to study the effects of different internal representations in a GA, which generates neural networks. A second GA was used to optimize the genome structure. This structure produces an optimized system within a shorter time interval.

Neural networks supporting autobiographical memory retrieval in posttraumatic stress disorder.

Posttraumatic stress disorder (PTSD) affects the functional recruitment and connectivity between neural regions during autobiographical memory (AM) retrieval that overlap with default and control networks. Whether such univariate changes relate to potential differences in the contributions of the large-scale neural networks supporting cognition in PTSD is unknown. In the present functional MRI study, we employed independent-component analysis to examine the influence of the engagement of neural networks during the recall of personal memories in a PTSD group (15 participants) as compared to non-trauma-exposed healthy controls (14 participants). We found that the PTSD group recruited similar neural networks when compared to the controls during AM recall, including default-network subsystems and control networks, but group differences emerged in the spatial and temporal characteristics of these networks. First, we found spatial differences in the contributions of the anterior and posterior midline across the networks, and of the amygdala in particular, for the medial temporal subsystem of the default network. Second, we found temporal differences within the medial prefrontal subsystem of the default network, with less temporal coupling of this network during AM retrieval in PTSD relative to controls. These findings suggest that the spatial and temporal characteristics of the default and control networks potentially differ in a PTSD group versus healthy controls and contribute to altered recall of personal memory.

Dynamic neural networks supporting memory retrieval.

How do separate neural networks interact to support complex cognitive processes such as remembrance of the personal past? Autobiographical memory (AM) retrieval recruits a consistent pattern of activation that potentially comprises multiple neural networks. However, it is unclear how such large-scale neural networks interact and are modulated by properties of the memory retrieval process. In the present functional MRI (fMRI) study, we combined independent component analysis (ICA) and dynamic causal modeling (DCM) to understand the neural networks supporting AM retrieval. ICA revealed four task-related components consistent with the previous literature: 1) medial prefrontal cortex (PFC) network, associated with self-referential processes, 2) medial temporal lobe (MTL) network, associated with memory, 3) frontoparietal network, associated with strategic search, and 4) cingulooperculum network, associated with goal maintenance. DCM analysis revealed that the medial PFC network drove activation within the system, consistent with the importance of this network to AM retrieval. Additionally, memory accessibility and recollection uniquely altered connectivity between these neural networks. Recollection modulated the influence of the medial PFC on the MTL network during elaboration, suggesting that greater connectivity among subsystems of the default network supports greater re-experience. In contrast, memory accessibility modulated the influence of frontoparietal and MTL networks on the medial PFC network, suggesting that ease of retrieval involves greater fluency among the multiple networks contributing to AM. These results show the integration between neural networks supporting AM retrieval and the modulation of network connectivity by behavior.

Synchrony between sensory and cognitive networks is associated with subclinical variation in autistic traits

© 2015 Young, Smith, Coutlee and Huettel.Individuals with autistic spectrum disorders exhibit distinct personality traits linked to attentional, social, and affective functions, and those traits are expressed with varying levels of severity in the neurotypical and subclinical population. Variation in autistic traits has been linked to reduced functional and structural connectivity (i.e., underconnectivity, or reduced synchrony) with neural networks modulated by attentional, social, and affective functions. Yet, it remains unclear whether reduced synchrony between these neural networks contributes to autistic traits. To investigate this issue, we used functional magnetic resonance imaging to record brain activation while neurotypical participants who varied in their subclinical scores on the Autism-Spectrum Quotient (AQ) viewed alternating blocks of social and nonsocial stimuli (i.e., images of faces and of landscape scenes). We used independent component analysis (ICA) combined with a spatiotemporal regression to quantify synchrony between neural networks. Our results indicated that decreased synchrony between the executive control network (ECN) and a face-scene network (FSN) predicted higher scores on the AQ. This relationship was not explained by individual differences in head motion, preferences for faces, or personality variables related to social cognition. Our findings build on clinical reports by demonstrating that reduced synchrony between distinct neural networks contributes to a range of subclinical autistic traits.

Artificial neural networks in modelling osmotic dehydration of foods

Artificial neural network (ANN) models for water loss (WL) and solid gain (SG) were evaluated as potential alternative to multiple linear regression (MLR) for osmotic dehydration of apple, banana and potato. The radial basis function (RBF) network with a Gaussian function was used in this study. The RBF employed the orthogonal least square learning method. When predictions of experimental data from MLR and ANN were compared, an agreement was found for ANN models than MLR models for SG than WL. The regression coefficient for determination (R2) for SG in MLR models was 0.31, and for ANN was 0.91. The R2 in MLR for WL was 0.89, whereas ANN was 0.84.Osmotic dehydration experiments found that the amount of WL and SG occurred in the following descending order: Golden Delicious apple > Cox apple > potato > banana. The effect of temperature and concentration of osmotic solution on WL and SG of the plant materials followed a descending order as: 55 > 40 > 32.2C and 70 > 60 > 50 > 40%, respectively.

A taxonomy for wavelet neural networks applied to nonlinear modelling

This article presents a novel classification of wavelet neural networks based on the orthogonality/non-orthogonality of neurons and the type of nonlinearity employed. On the basis of this classification different network types are studied and their characteristics illustrated by means of simple one-dimensional nonlinear examples. For multidimensional problems, which are affected by the curse of dimensionality, the idea of spherical wavelet functions is considered. The behaviour of these networks is also studied for modelling of a low-dimension map.

A new Jacobian matrix for optimal learning of single-layer neural networks

This paper investigates the learning of a wide class of single-hidden-layer feedforward neural networks (SLFNs) with two sets of adjustable parameters, i.e., the nonlinear parameters in the hidden nodes and the linear output weights. The main objective is to both speed up the convergence of second-order learning algorithms such as Levenberg-Marquardt (LM), as well as to improve the network performance. This is achieved here by reducing the dimension of the solution space and by introducing a new Jacobian matrix. Unlike conventional supervised learning methods which optimize these two sets of parameters simultaneously, the linear output weights are first converted into dependent parameters, thereby removing the need for their explicit computation. Consequently, the neural network (NN) learning is performed over a solution space of reduced dimension. A new Jacobian matrix is then proposed for use with the popular second-order learning methods in order to achieve a more accurate approximation of the cost function. The efficacy of the proposed method is shown through an analysis of the computational complexity and by presenting simulation results from four different examples.

Estimation of ternary liquid-liquid equilibria for arene/alkane/ionic liquid mixtures using neural networks

Neural network models have been explored for the prediction of the liquid-liquid equilibrium data and aromatic/aliphatic selectivity values. Four ternary systems composed of toluene, heptane, and the ionic liquids 1-ethyl-3-methylimidazolium ethylsulfate, or 1,3-dimethylimidazolium methylsulfate were investigated at 313.2 and 348.2 K.