Deep Reinforcement Learning uses a deep neural network to encode a policy, which achieves very good performance in a wide range of applications but is widely regarded as a black box model. A more interpretable alternative to deep networks is given by neuro-fuzzy controllers. Unfortunately, neuro-fuzzy controllers often need a large number of rules to solve relatively simple tasks, making them difficult to interpret. In this work, we present an algorithm to distill the policy from a deep Q-network into a compact neuro-fuzzy controller. This allows us to train compact neuro-fuzzy controllers through distillation to solve tasks that they are unable to solve directly, combining the flexibility of deep reinforcement learning and the interpretability of compact rule bases. We demonstrate the algorithm on three well-known environments from OpenAI Gym, where we nearly match the performance of a DQN agent using only 2 to 6 fuzzy rules.
Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework
Dept. of EECS, Syracuse University, NY 13244, USA（电子工程与计算机科学系， Syracuse大学，纽约州，13244，美国）；Air Force Research Laboratory, Rome, NY 13441, USA（空军研究实验室，罗马，纽约州，13441，美国）
Spiking neural network (SNN), compared with depth neural network (DNN), has faster processing speed, lower energy consumption and more biological interpretability, which is expected to approach Strong AI. Reinforcement learning is similar to learning in biology. It is of great significance to study the combination of SNN and RL. We propose the reinforcement learning method of spike distillation network (SDN) with STBP. This method uses distillation to effectively avoid the weakness of STBP, which can achieve SOTA performance in classification, and can obtain a smaller, faster convergence and l…
China University of Petroleum (East China)（中国石油大学（华东））；Indian Statistical Institute（印度统计研究所）
A major limitation of fuzzy or neuro-fuzzy systems is their failure to deal with high-dimensional datasets. This happens primarily due to the use of T-norm, particularly, product or minimum (or a softer version of it). Thus, there are hardly any work dealing with datasets with dimensions more than hundred or so. Here, we propose a neuro-fuzzy framework that can handle datasets with dimensions even more than 7000! In this context, we propose an adaptive softmin (Ada-softmin) which effectively overcomes the drawbacks of ``numeric underflow" and ``fake minimum" that arise for existing fuzzy syste…
User knowledge modeling systems are used as the most effective technology for grabbing new user's attention. Moreover, the quality of service (QOS) is increased by these intelligent services. This paper proposes two user knowledge classifiers based on artificial neural networks used as one of the influential parts of knowledge modeling systems. We employed multi-layer perceptron (MLP) and adaptive neural fuzzy inference system (ANFIS) as the classifiers. Moreover, we used real data contains the user's degree of study time, repetition number, their performance in exam, as well as the learning p…
Functional Electrical Stimulation (FES) can restore motion to a paralysed person's muscles. Yet, control stimulating many muscles to restore the practical function of entire limbs is an unsolved problem. Current neurostimulation engineering still relies on 20th Century control approaches and correspondingly shows only modest results that require daily tinkering to operate at all. Here, we present our state of the art Deep Reinforcement Learning (RL) developed for real time adaptive neurostimulation of paralysed legs for FES cycling. Core to our approach is the integration of a personalised neu…
In this paper, an interpretable classifier using an interval type-2 fuzzy neural network for detecting patients suffering from Parkinson's Disease (PD) based on analyzing the gait cycle is presented. The proposed method utilizes clinical features extracted from the vertical Ground Reaction Force (vGRF), measured by 16 wearable sensors placed in the soles of subjects' shoes and learns interpretable fuzzy rules. Therefore, experts can verify the decision made by the proposed method based on investigating the firing strength of interpretable fuzzy rules. Moreover, experts can utilize the extracte…
Universiti Malaysia Terengganu（马来西亚登嘉楼大学）；Universiti Tecknologi Malaysia（马来西亚工艺大学）
Most of researches on image forensics have been mainly focused on detection of artifacts introduced by a single processing tool. They lead in the development of many specialized algorithms looking for one or more particular footprints under specific settings. Naturally, the performance of such algorithms are not perfect, and accordingly the provided output might be noisy, inaccurate and only partially correct. Furthermore, a forged image in practical scenarios is often the result of utilizing several tools available by image-processing software systems. Therefore, reliable tamper detection req…
Xsensor Technology Corp（Xsensor科技公司）；University of Alberta（阿尔伯塔大学）
The combination of neural network and fuzzy systems into neuro-fuzzy systems integrates fuzzy reasoning rules into the connectionist networks. However, the existing neuro-fuzzy systems are developed under shallow structures having lower generalization capacity. We propose the first end-to-end deep neuro-fuzzy network and investigate its application for image classification. Two new operations are developed based on definitions of Takagi-Sugeno-Kang (TSK) fuzzy model namely fuzzy inference operation and fuzzy pooling operations; stacks of these operations comprise the layers in this network. We…
Data mining techniques can be used to discover useful patterns by exploring and analyzing data and it's feasible to synergitically combine machine learning tools to discover fuzzy classification rules.In this paper, an adaptive Neuro fuzzy network with TSK fuzzy type and an improved quantum subtractive clustering has been developed. Quantum clustering (QC) is an intuition from quantum mechanics which uses Schrodinger potential and time-consuming gradient descent method. The principle advantage and shortcoming of QC is analyzed and based on its shortcomings, an improved algorithm through a subt…
Explainable Uncertainty Quantification for Wastewater Treatment Energy Prediction via Interval Type-2 Neuro-Fuzzy System
Jheronimus Academy of Data Science, Eindhoven University of Technology, Eindhoven, The Netherlands（杰罗尼穆斯数据科学学院，埃因霍温理工大学，埃因霍温，荷兰）；Haskoning, Amersfoort, The Netherlands（哈索宁，阿默斯福尔特，荷兰）；School of Industrial Engineering, Eindhoven University of Technology（工业工程学院，埃因霍温理工大学）
Simple power electronic drive circuit and fault tolerance of converter are specific advantages of SRM drives, but excessive torque ripple has limited its use to special applications. It is well known that controlling the current shape adequately can minimize the torque ripple. This paper presents a new method for shaping the motor currents to minimize the torque ripple, using a neuro-fuzzy compensator. In the proposed method, a compensating signal is added to the output of a PI controller, in a current-regulated speed control loop. Numerical results are presented in this paper, with an analysi…
NASP-T: A Fuzzy Neuro-Symbolic Transformer for Logic-Constrained Aviation Safety Report Classification
Faculty of Science and Technology (REALTEK)（科学与技术学院）；Norwegian University of Life Sciences (NMBU)（挪威生命科学大学）；Dresden International University (DIU)（德累斯顿国际大学）
Delhi Technological University（德里理工大学）；Dehradun Institute of Technology（德拉敦理工学院）
Most important reason for project failure is poor effort estimation. Software development effort estimation is needed for assigning appropriate team members for development, allocating resources for software development, binding etc. Inaccurate software estimation may lead to delay in project, over-budget or cancellation of the project. But the effort estimation models are not very efficient. In this paper, we are analyzing the new approach for estimation i.e. Neuro Fuzzy Inference System (NFIS). It is a mixture model that consolidates the components of artificial neural network with fuzzy log…
Increasing demands in performance and quality make drive systems fundamental parts in the progressive automation of industrial processes. Their conventional models become inappropriate and have limited scope if one requires a precise and fast performance. So, it is important to incorporate learning capabilities into drive systems in such a way that they improve their accuracy in realtime, becoming more autonomous agents with some degree of intelligence. To investigate this challenge, this chapter presents the development of a learning control system that uses neuro-fuzzy techniques in the desi…
Gradient-Based Neuroplastic Adaptation for Concurrent Optimization of Neuro-Fuzzy Networks
Department of Analytics and Information Systems at Western Kentucky University（威斯康星大学西部分校分析与信息系统系）；Department of Computer Science at North Carolina State University（北卡罗来纳州立大学计算机科学系）
Institute of advanced studies（高级研究院）；Alba Regia Technical Faculty（阿尔巴雷吉亚技术学院）；Obuda University（欧布达大学）；University of Pannonia（潘诺尼亚大学）；J. Selye University（赛利耶大学）；Bauhaus Universität Weimar（魏玛包豪斯大学）
Hybridization of machine learning methods with soft computing techniques is an essential approach to improve the performance of the prediction models. Hybrid machine learning models, particularly, have gained popularity in the advancement of the high-performance control systems. Higher accuracy and better performance for prediction models of exergy destruction and energy consumption used in the control circuit of heating, ventilation, and air conditioning (HVAC) systems can be highly economical in the industrial scale to save energy. This research proposes two hybrid models of adaptive neuro-f…
Interpretable Fuzzy Modeling Reveals Population-Level Representation Differences in P300 Brain Computer Interfaces Across Neurodivergent and Neurotypical Cohorts
Department of Management, Griffith Business School（管理学院，格里菲斯商学院）；Department of Neuroscience, Perelman School of Medicine, University of Pennsylvania（神经科学系，佩尔曼医学学院，宾夕法尼亚大学）；Marketing Department, Wharton School of Business, University of Pennsylvania（营销系，沃顿商学院，宾夕法尼亚大学）；Department of Psychology, School of Arts and Sciences, University of Pennsylvania（心理学系，艺术与科学学院，宾夕法尼亚大学）
University of Technology Sydney（悉尼科技大学）；Advanced Analytics Institute（高级分析研究所）；Faculty of Engineering and Information Technology（工程与信息技术学院）
General fuzzy min-max neural network (GFMMNN) is one of the efficient neuro-fuzzy systems for data classification. However, one of the downsides of its original learning algorithms is the inability to handle and learn from the mixed-attribute data. While categorical features encoding methods can be used with the GFMMNN learning algorithms, they exhibit a lot of shortcomings. Other approaches proposed in the literature are not suitable for on-line learning as they require entire training data available in the learning phase. With the rapid change in the volume and velocity of streaming data in …
Recurrent Neural Networks (RNNs) are a key technology for applications such as automatic speech recognition or machine translation. Unlike conventional feed-forward DNNs, RNNs remember past information to improve the accuracy of future predictions and, therefore, they are very effective for sequence processing problems. For each application run, recurrent layers are executed many times for processing a potentially large sequence of inputs (words, images, audio frames, etc.). In this paper, we observe that the output of a neuron exhibits small changes in consecutive invocations.~We exploit this…
Kalman Kando Faculty of Electrical Engineering, Obuda University（欧布达大学卡尔曼·坎多电气工程学院）；John von Neumann Faculty of Informatics, Obuda University（欧布达大学约翰·冯·诺依曼信息学院）
The accurate prediction of the solar Diffuse Fraction (DF), sometimes called the Diffuse Ratio, is an important topic for solar energy research. In the present study, the current state of Diffuse Irradiance research is discussed and then three robust, Machine Learning (ML) models, are examined using a large dataset (almost 8 years) of hourly readings from Almeria, Spain. The ML models used herein, are a hybrid Adaptive Network-based Fuzzy Inference System (ANFIS), a single Multi-Layer Perceptron (MLP) and a hybrid Multi-Layer Perceptron-Grey Wolf Optimizer (MLP-GWO). These models were evaluate…
The U.S. water distribution system contains thousands of miles of pipes constructed from different materials, and of various sizes, and age. These pipes suffer from physical, environmental, structural and operational stresses, causing deterioration which eventually leads to their failure. Pipe deterioration results in increased break rates, reduced hydraulic capacity, and detrimental impacts on water quality. Therefore, it is crucial to use accurate models to forecast deterioration rates along with estimating the remaining useful life of the pipes to implement essential interference plans in o…
Shenyang Sport University（沈阳体育学院）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；State University of New York at Binghamton（纽约州立大学宾汉姆顿分校）；Northeastern University（东北大学）
In recent decades, one of the scientists' main concerns has been to improve the accuracy of satellite attitude, regardless of the expense. The obvious result is that a large number of control strategies have been used to address this problem. In this study, an adaptive neuro-fuzzy integrated (ANFIS) satellite attitude estimation and control system was developed. The controller is trained with the data provided by an optimal controller. A pulse modulator is used to generate the right ON/OFF commands of the thruster actuator. To evaluate the performance of the AN-FIS controller in closed-loop si…
Institute of Research and Development, Duy Tan University（大越大学研究与发展学院）；Obuda University（欧布达大学）；Oxford Brookes University（牛津布鲁克斯大学）；Ton Duc Thang University（同塔大学）；Hong Kong Polytechnic University（香港理工大学）
Climate change impacts and adaptations are the subjects to ongoing issues that attract the attention of many researchers. Insight into the wind power potential in an area and its probable variation due to climate change impacts can provide useful information for energy policymakers and strategists for sustainable development and management of the energy. In this study, spatial variation of wind power density at the turbine hub-height and its variability under future climatic scenarios are taken under consideration. An ANFIS based post-processing technique was employed to match the power output…
School of Electronics Engineering, Kyungpook National University（庆北国立大学电子工程学院）
Generating music with emotion similar to that of an input video is a very relevant issue nowadays. Video content creators and automatic movie directors benefit from maintaining their viewers engaged, which can be facilitated by producing novel material eliciting stronger emotions in them. Moreover, there's currently a demand for more empathetic computers to aid humans in applications such as augmenting the perception ability of visually and/or hearing impaired people. Current approaches overlook the video's emotional characteristics in the music generation step, only consider static images ins…
Numerous neuro-symbolic approaches have recently been proposed typically with the goal of adding symbolic knowledge to the output layer of a neural network. Ideally, such losses maximize the probability that the neural network's predictions satisfy the underlying domain. Unfortunately, this type of probabilistic inference is often computationally infeasible. Neuro-symbolic approaches therefore commonly resort to fuzzy approximations of this probabilistic objective, sacrificing sound probabilistic semantics, or to sampling which is very seldom feasible. We approach the problem by first assuming…
We revisit fuzzy neural network with a cornerstone notion of generalized hamming distance, which provides a novel and theoretically justified framework to re-interpret many useful neural network techniques in terms of fuzzy logic. In particular, we conjecture and empirically illustrate that, the celebrated batch normalization (BN) technique actually adapts the normalized bias such that it approximates the rightful bias induced by the generalized hamming distance. Once the due bias is enforced analytically, neither the optimization of bias terms nor the sophisticated batch normalization is need…
Recent work on neuro-symbolic inductive logic programming has led to promising approaches that can learn explanatory rules from noisy, real-world data. While some proposals approximate logical operators with differentiable operators from fuzzy or real-valued logic that are parameter-free thus diminishing their capacity to fit the data, other approaches are only loosely based on logic making it difficult to interpret the learned "rules". In this paper, we propose learning rules with the recently proposed logical neural networks (LNN). Compared to others, LNNs offer strong connection to classica…
Architectural change in neural networks using fuzzy vertex pooling
Department of General Science, Birla Institute of Technology and Science Pilani, International Academic City（一般科学系，比拉理工学院和科学学院，国际学术城）；Department of Mathematics, Providence Women’s College, Calicut, India（数学系，普罗维登斯女子学院，卡利卡特，印度）；Department of Mathematics, National Institute of Technology, Calicut, India（数学系，国家理工学院，卡利卡特，印度）
A general fuzzy min-max (GFMM) neural network is one of the efficient neuro-fuzzy systems for classification problems. However, a disadvantage of most of the current learning algorithms for GFMM is that they can handle effectively numerical valued features only. Therefore, this paper provides some potential approaches to adapting GFMM learning algorithms for classification problems with mixed-type or only categorical features as they are very common in practical applications and often carry very useful information. We will compare and assess three main methods of handling datasets with mixed f…
Zhejiang University of Technology（浙江工业大学）；National Yunlin University of Science and Technology（云林科技大学）；J. Selye University（J.塞莱大学）；The Hong Kong Polytechnic University（香港理工大学）；Obuda University（奥布达大学）；Slovak University of Technology in Bratislava（布拉迪斯拉发斯洛伐克技术大学）
In this research, dew point temperature (DPT) is simulated using the data-driven approach. Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized as a data-driven technique to forecast this parameter at Tabriz in East Azerbaijan. Various input patterns, namely T min, T max, and T mean, are utilized for training the architecture whilst DPT is the model's output. The findings indicate that, in general, ANFIS method is capable of identifying data patterns with a high degree of accuracy. However, the approach demonstrates that processing time and computer resources may substantially increase by…
