Connectionist Methods Research Articles

Analysis of article type category based on KNN

Natural Language Processing (NLP) boasts a rich historical background, evolving since the 1950s at the crossroads of artificial intelligence and linguistics. Over time, it has seamlessly converged with Information Retrieval (IR), adopting diverse approaches encompassing symbolic, statistical, and connectionist methods. This study focuses on the utilization of the k-nearest neighbours (KNN) algorithm for the categorization of articles. It delves into the feasibility of accurately classifying articles when provided with ample datasets and clearly defined category labels. Through the development of a model and the integration of the KNN algorithm, this experiment successfully conducted content-based article classification. By selecting an appropriate value for k, employing a confusion matrix for performance assessment, and predicting article categories, the experiment achieved an accuracy rate of 0.96. Nonetheless, limitations arise when dealing with small datasets or imbalanced article distributions. This paper delves into the intricacies of article type classification, emphasizing the pivotal roles of data quality and feature engineering in this process. Furthermore, it underscores the potential for in-depth exploration in various contexts using alternative methodologies, such as Bayesian, Support Vector Machines, and deep learning, providing valuable references for future research endeavours.

Neural-symbolic BDI-Agent as a Multi-Context System: A case study with negotiating agent

Intelligent systems are already being deployed in several fields (e.g., medicine, education, automation, or legal), providing relevant tools to assist in our daily tasks. It is claimed that the next step of AI is the integration of connectionist and symbolic methods. Connectionist methods embody knowledge by assigning numerical conductivities or weights to the connections inside a network of nodes. Symbolic methods work by carrying on a sequence of logic-like reasoning steps over a set of symbols consisting of language-like representations. Combining the strengths of connectionist and symbolic methods can allow the development of robust intelligent systems. We propose a neural-symbolic BDI-agent based Multi-Context Systems (MCS) model to integrate these two methods. Neural-symbolic area explores the effective integration of connectionist and symbolic methods, more precisely, learning and reasoning. MCSs allow the representation of information exchange among heterogeneous sources. BDI-agents offer robust and flexible behavior, rapid and modular development, intelligibility, and verifiability. In our work, MCSs represent the symbolic method and Neural Networks the connectionist method. We present a case study of how the proposed agent can be implemented using the Sigon framework. Sigon facilitates the development of MCS agents using a programming language-like paradigm. In this case study, we employed a trained MultiLayer Perceptron (MLP) neural network, enabling us to mitigate the necessity of modeling some hand-crafted rules in symbolic systems. We performed two experiments, in which the main goal was to analyze the impact of using a neural network during the agent’s decision-making. In the first experiment, we compare the proposed agent with 136 negotiating agents participating in the Automated Negotiating Agents Competition (ANAC) available on the GENIUS framework. In the second experiment, we compare our work with one similar to ours. The results show that our agent can adapt and achieve high utility functions for different situations. However, it is necessary to consider the computational cost of using the NN’s output in every reasoning cycle. The contributions of this paper are: (i) - integration of connectionist methods as part of the agent’s decision-making, enabling the development of agents in a modular and flexible fashion; (ii) - custom sensors to handle different data types; (iii) - practical implementation of the proposed integration method; and (iv) - experiments of the proposed integration method, focusing on mitigating the necessity of hard-coded and hand-crafted rules.

SGL: Symbolic Goal Learning in a Hybrid, Modular Framework for Human Instruction Following

This paper investigates human instruction following for robotic manipulation via a hybrid, modular system with symbolic and connectionist elements. Symbolic methods build modular systems with semantic parsing and task planning modules for producing sequences of actions from natural language requests. Modern connectionist methods employ deep neural networks that learn visual and linguistic features for mapping inputs to a sequence of low-level actions, in an end-to-end fashion. The hybrid, modular system blends these two approaches to create a modular framework: it formulates instruction following as symbolic goal learning via deep neural networks followed by task planning via symbolic planners. Connectionist and symbolic modules are bridged with Planning Domain Definition Language. The vision-and-language learning network predicts its goal representation, which is sent to a planner for producing a task-completing action sequence. For improving the flexibility of natural language, we further incorporate implicit human intents with explicit human instructions. To learn generic features for vision and language, we propose to separately pretrain vision and language encoders on scene graph parsing and semantic textual similarity tasks. Benchmarking evaluates the impacts of different components of, or options for, the vision-and-language learning model and shows the effectiveness of pretraining strategies. Manipulation experiments conducted in the simulator AI2THOR show the robustness of the framework to novel scenarios.

An Expert Model Based on Physics-Aware Neural Network for the Prediction of Thermal Conductivity of Nanofluids

Abstract Operating fluids are always a significant factor for not achieving a good enough performance of heat transfer equipment and also for growing the energy costs. To resolve this issue, nanofluids are considered a potential choice for conventional heat transfer fluids due to their efficiency for the improvement of overall thermal performance. The aim of this research is to propose a physics-guided machine learning approach by incorporating physics-based relations at the initial stage and into traditional loss functions for predicting the thermal conductivity of water-based nanofluids using a wide range of both experimental and simulated data of nanoparticles Al2O3, CuO, and TiO2. Further, smart connectionist methods, viz., ridge regression, lasso regression, random forest, extreme gradient boosting (xgboost (XGB)), and black-box multilayer perceptron (MLP) are applied to compare the present physics-aware MLP model based on different statistical indicators. The accuracy analyses reveal that the use of physical views to monitor the learning of neural networks shows better results with mean absolute percentage error (MAPE) = 0.7075%, root-mean-squared error (RMSE) = 0.0042 W/mK, and R2 = 0.9525. The temperature and volume concentration variations are discussed graphically. Furthermore, the outcomes of applied algorithms confirm that the well-known theoretical and computer-aided models show substandard results than the proposed model.

Empirical, statistical, and connectionist methods coupled with log variables ranking for the prediction of pore network permeability in a heterogeneous oil reservoir

Empirical, statistical, and connectionist methods coupled with log variables ranking for the prediction of pore network permeability in a heterogeneous oil reservoir

Modeling somatic computation with non-neural bioelectric networks

The field of basal cognition seeks to understand how adaptive, context-specific behavior occurs in non-neural biological systems. Embryogenesis and regeneration require plasticity in many tissue types to achieve structural and functional goals in diverse circumstances. Thus, advances in both evolutionary cell biology and regenerative medicine require an understanding of how non-neural tissues could process information. Neurons evolved from ancient cell types that used bioelectric signaling to perform computation. However, it has not been shown whether or how non-neural bioelectric cell networks can support computation. We generalize connectionist methods to non-neural tissue architectures, showing that a minimal non-neural Bio-Electric Network (BEN) model that utilizes the general principles of bioelectricity (electrodiffusion and gating) can compute. We characterize BEN behaviors ranging from elementary logic gates to pattern detectors, using both fixed and transient inputs to recapitulate various biological scenarios. We characterize the mechanisms of such networks using dynamical-systems and information-theory tools, demonstrating that logic can manifest in bidirectional, continuous, and relatively slow bioelectrical systems, complementing conventional neural-centric architectures. Our results reveal a variety of non-neural decision-making processes as manifestations of general cellular biophysical mechanisms and suggest novel bioengineering approaches to construct functional tissues for regenerative medicine and synthetic biology as well as new machine learning architectures.

Machine learning models to predict bottom hole pressure in multi‐phase flow in vertical oil production wells

The precise estimation of a pressure drop in vertical multiphase flowing oil wells plays a crucial role in designing robust production facilities and evaluating optimum production plans. A significant amount of research has been conducted on determining a pressure drop via calculating the bottom hole pressure (BHP); these different methods as well as numerical, analytical, semi‐analytical, and empirical correlations can be used for doing this task. Unfortunately, most of those correlations are unable to provide reasonable precision when calculating BHP and, consequently, improvements are still required. To predict BHP in vertical wells, several hybrids of meta‐heuristic optimization methods and a bio‐inspired connectionist approach, i.e., artificial neural network (ANN), are employed. The main goal of these optimization algorithms is to optimize the parameters of the ANN models, i.e., weights and biases, to improve their performance. Based on the obtained outputs and various robustness indexes, a hybrid genetic algorithm and particle swarm optimization (HGAPSO) is highly precise and has a maximum of 10 % error compared to measured pressure data. The results of this work reveal the capability of those hybrid connectionist models for predicting the BHP of multi‐phase flow in vertical wells; these results demonstrate the promising use of connectionist methods in commercial production software in the near future.

Complexity Theory: An Overview with Potential Applications for the Social Sciences

Systems theory has been challenged in the recent literature due to its perceived disconnection from today’s research and practice demands. Moving away from the reductionist frameworks and the complicated domain predominated by known unknowns and order, a call is being made to the social sciences to begin adopting complexity theory and newer connectionist methods that better address complexity and open social systems. Scholars and scholar-practitioners will continue to find the need to apply complexity theory as wicked problems become more prevalent in the social sciences. This paper differentiates between general systems theory (GST) and complexity theory, as well as identifies advantages for the social sciences in incorporating complexity theory as a formal theory. Complexity theory is expanded upon and identified as providing a new perspective and a new method of theorizing that can be practiced by disciplines within the social sciences. These additions could better position the social sciences to address the complexity associated with advancing technology, globalization, intricate markets, cultural change, and the myriad of challenges and opportunities to come.

Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithms

ABSTRACTDynamic viscosity considerably affects the heat transfer and flow of fluids. Due to improved thermophysical properties of fluids containing nanostructures, these types of fluids are widely employed in thermal mediums. The nanofluid's dynamic viscosity relies on different variables including size of solid phase, concentration and temperature. In the present study, three algorithms including multivariable polynomial regression (MPR), artificial neural network–multilayer perceptron (ANN-MLP) and multivariate adaptive regression splines (MARS) are applied to model the dynamic viscosity of silver (Ag)/water nanofluid. Recently published experimental investigations are employed for data extraction. The input variables considered in the modeling process to be the most important ones are the size of particles, fluid temperature and the concentration of Ag nanoparticles in the base fluid. The R2 values for the studied models are 0.9998, 0.9997 and 0.9996 for the ANN-MLP, MARS and MPR algorithms, respectively. In addition, based on importance analysis, the temperature is highly effective and the dominant parameter for the dynamic viscosity of the nanofluid in comparison with size and concentration.

Applicability of connectionist methods to predict thermal resistance of pulsating heat pipes with ethanol by using neural networks

Pulsating heat pipes (PHPs) are compact and efficient devices in heat transfer which are applicable for several purposes. The thermal resistance of PHPs depends on several parameters. In the present study, four models including multilayer perceptron (MLP), radial bias function (RBF), conjugated hybrid of particle swarm optimization and adaptive neuro-fuzzy inference system (CHPSO ANFIS) are applied to predict the thermal resistance of pulsating heat pipes filled with ethanol. The obtained results indicated that the radial bias function (RBF) model had the highest accuracy among the applied models and can predict the thermal resistance of the PHPs precisely. The R-squared and root mean squared error (RMSE) values for this model were 0.9892 and 0.0650, respectively.

Thermal conductivity ratio prediction of Al2O3/water nanofluid by applying connectionist methods

Various parameters affect thermal conductivity of nanofluid; however, some of them are more influential such as temperature, size and type of nano particles and volumetric concentration. In this study, artificial neural network as well as least square support vector machine (LSSVM) are applied in order to predict thermal conductivity ratio of alumina/water nanofluid as a function of particle size, temperature and volumetric concentration. LSSVM, Self-Organizing Map and Levenberg-Marquardt Back Propagation algorithms are applied to predict thermal conductivity ratio. Obtained results indicated that these algorithms are appropriate tool for thermal conductivity ratio prediction. The correlation coefficient values are very favorable and equal to 0.88125 and 0.87575 and 0.89999 by applying SOM, LM-BP algorithms and LSSVM, respectively.

Extension of grounding mechanism for abstract words: computational methods insights

The attempts to model cognitive phenomena effectively have split the research community in two paradigms: symbolic and connectionist. The extension of grounding phenomenon for abstract words is very important for social interactions of cognitive robots in real scenarios. This paper reviews the strength of symbolic and connectionist methods to address the abstract word grounding problem in cognitive robots. In particular, the presented work is focused on designing and simulating cognitive robotics model to achieve a grounding mechanism for abstract words by using the semantic network approach, as well as examining the utility of connectionist computation for the same problem. Two neuro-robotics models based on feed forward neural network and recurrent neural network are presented to see the pros and cons of connectionist approach. The simulation results and review of attributes of these methods reveal that the proposed symbolic model offers the solution to the problem of grounding abstract words with attributes like high data storage capacity with recall accuracy, structural integrity and temporal sequence handling. Whereas, connectionist computation based solutions give more natural solution to this problem with some shortcomings that include combinatorial ambiguity, low storage capacity and structural rigidity. The presented results are not only important for the advancement in communication system of cognitive robot, also provide evidence for embodied nature of abstract language.

Tool wear monitoring and prognostics challenges: a comparison of connectionist methods toward an adaptive ensemble model

In a high speed milling operation the cutting tool acts as a backbone of machining process, which requires timely replacement to avoid loss of costly workpiece or machine downtime. To this aim, prognostics is applied for predicting tool wear and estimating its life span to replace the cutting tool before failure. However, the life span of cutting tools varies between minutes or hours, therefore time is critical for tool condition monitoring. Moreover, complex nature of manufacturing process requires models that can accurately predict tool degradation and provide confidence for decisions. In this context, a data-driven connectionist approach is proposed for tool condition monitoring application. In brief, an ensemble of Summation Wavelet-Extreme Learning Machine models is proposed with incremental learning scheme. The proposed approach is validated on cutting force measurements data from Computer Numerical Control machine. Results clearly show the significance of our proposition.

Optimizing Back-Propagation Gradient for Classification by an Artificial Neural Network

In a complex and changing a remote sensing system, which requires taking quick and informed decisions environment, connectionist methods have shown their great contribution in particular the reduction and classification of spectral data. In this context, this paper proposes to study the parameters that optimize the results of an artificial neural network ANN multilayer perceptron based, for classification of chemical agents on multi-spectral images. The mean squared error cost function remains one of the major parameters of the network convergence at its learning phase and a challenge that will face our approach to improve the gradient descent by the conjugate gradient method that seems fast and efficient.

Computational Modeling in Developmental Psychology

This manuscript surveys computational modeling efforts by researchers in developmental psychology. Developmental psychology is ready to blossom into a modern science that focuses on causal mechanistic explanations of development rather than just describing and classifying behaviors. Computational modeling is the key to this process. However, to be effective, models must not only mimic observed data. They must also be transparent, grounded, and plausible to be accepted by the developmental psychology community. Connectionist model provides one such example. Many developmental features of typical and atypical perception, cognition, and language have been modeled using connectionist methods. Successful models are closely tied to the details of existing empirical studies and make concrete testable predictions. The success of such a project relies on the close collaboration of computational scientists with empirical psychologists

A connectionist model for variable binding, case role assignment and inference in language processing

Humans have the capability of processing language and drawing inferences effortlessly. This raises a question as to how neurons in the brain process language and inference. Although connectionism is one of the promising candidates of methods for studying brain functions, it is not clear so far whether or not connectionist methods can be used to model the full range of cognitive functions like language processing or inference. Language processing involves several functional properties, such as variable binding, sequential data processing, case role assignment, inference and memory. Here, we propose a simple connectionist model, which can deal with some of these properties.

Symbolic vs. connectionist learning: an experimental comparison in a structured domain

During the last two decades, the attempts to find effective solutions to the problem of learning any kind of structured information have been splitting the scientific community. A "holy war" has been fought between the advocates of a symbolic approach to learning and the advocates of a connectionist approach. One of the most repeated claims of the symbolic party has been that symbolic methods are able to cope with structured information while connectionist ones are not. However, in the last few years, the possibility of employing connectionist methods for structured data has been widely investigated and several approaches have been proposed. A novel algorithm for learning structured descriptions, ascribable to the category of symbolic techniques, is proposed. It faces the problem directly in the space of graphs by defining the proper inference operators, as graph generalization and graph specialization, and obtains general and consistent prototypes with a low computational cost with respect to other symbolic learning systems. The proposed algorithm is compared with a recent connectionist method for learning structured data (P. Frasconi et al., 1998), with reference to a problem of handwritten character recognition from a standard database on the Web. The orthogonality of the two approaches strongly suggests their combination in a multiclassifier system so as to retain the strengths of both of them, while overcoming their weaknesses. The results on an experimental case study demonstrated that the adoption of a parallel combination scheme of the two algorithms could improve the recognition performance by about 10 percent. A truce or an alliance between the symbolic and the connectionist worlds?.

Evolving fuzzy neural networks for supervised/unsupervised online knowledge-based learning

This paper introduces evolving fuzzy neural networks (EFuNNs) as a means for the implementation of the evolving connectionist systems (ECOS) paradigm that is aimed at building online, adaptive intelligent systems that have both their structure and functionality evolving in time. EFuNNs evolve their structure and parameter values through incremental, hybrid supervised/unsupervised, online learning. They can accommodate new input data, including new features, new classes, etc., through local element tuning. New connections and new neurons are created during the operation of the system. EFuNNs can learn spatial-temporal sequences in an adaptive way through one pass learning and automatically adapt their parameter values as they operate. Fuzzy or crisp rules can be inserted and extracted at any time of the EFuNN operation. The characteristics of EFuNNs are illustrated on several case study data sets for time series prediction and spoken word classification. Their performance is compared with traditional connectionist methods and systems. The applicability of EFuNNs as general purpose online learning machines, what concerns systems that learn from large databases, life-long learning systems, and online adaptive systems in different areas of engineering are discussed.

A New Approach To Speech Coding: the Neural Predictive Coding

In this article we propose a new speech signal coding model applied to the recognition of phonemes. This model is an extension to the non linear area of adaptive coding systems used in speech processing. For this purpose, we use predictive connectionist methods. We show that it is possible to take into account class membership information of the phonemes from the stage of coding. To evaluate the NPC encoder, a study of a database of phonemes by discriminant analysis and an application to phonemes recognition are carried out. Simulations presented here show that classification has obviously been improved, compared to currently used types of coding.

Globally optimal fuzzy decision trees for classification and regression

A fuzzy decision tree is constructed by allowing the possibility of partial membership of a point in the nodes that make up the tree structure. This extension of its expressive capabilities transforms the decision tree into a powerful functional approximant that incorporates features of connectionist methods, while remaining easily interpretable. Fuzzification is achieved by superimposing a fuzzy structure over the skeleton of a CART decision tree. A training rule for fuzzy trees, similar to backpropagation in neural networks, is designed. This rule corresponds to a global optimization algorithm that fixes the parameters of the fuzzy splits. The method developed for the automatic generation of fuzzy decision trees is applied to both classification and regression problems. In regression problems, it is seen that the continuity constraint imposed by the function representation of the fuzzy tree leads to substantial improvements in the quality of the regression and limits the tendency to overfitting. In classification, fuzzification provides a means of uncovering the structure of the probability distribution for the classification errors in attribute space. This allows the identification of regions for which the error rate of the tree is significantly lower than the average error rate, sometimes even below the Bayes misclassification rate.