Unsupervised Learning Mechanism Research Articles

Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction

Finding reliable condition monitoring solutions for large-scale complex systems is currently a major challenge in industrial research. Since fault diagnosis is directly related to the features of a system, there have been many research studies aimed to develop methods for the selection of the relevant features. Moreover, there are no universal features for a particular application domain such as machine diagnosis. For example, in machine bearing fault diagnosis, these features are often selected by an expert or based on previous experience. Thus, for each bearing machine type, the relevant features must be selected. This paper attempts to solve the problem of relevant features identification by building an automatic fault diagnosis process based on relevant feature selection using a data-driven approach. The proposed approach starts with the extraction of the time-domain features from the input signals. Then, a feature reduction algorithm based on cross-correlation filter is applied to reduce the time and cost of the processing. Unsupervised learning mechanism using K-means++ selects the relevant fault features based on the squared Euclidian distance between different health states. Finally, the selected features are used as inputs to a self-organizing map producing our health indicator. The proposed method is tested on roller bearing benchmark datasets.

Network Supervision of Adult Experience and Learning Dependent Sensory Cortical Plasticity.

The brain is capable of remodeling throughout life. The sensory cortices provide a useful preparation for studying neuroplasticity both during development and thereafter. In adulthood, sensory cortices change in the cortical area activated by behaviorally relevant stimuli, by the strength of response within that activated area, and by the temporal profiles of those responses. Evidence supports forms of unsupervised, reinforcement, and fully supervised network learning rules. Studies on experience-dependent plasticity have mostly not controlled for learning, and they find support for unsupervised learning mechanisms. Changes occur with greatest ease in neurons containing α-CamKII, which are pyramidal neurons in layers II/III and layers V/VI. These changes use synaptic mechanisms including long term depression. Synaptic strengthening at NMDA-containing synapses does occur, but its weak association with activity suggests other factors also initiate changes. Studies that control learning find support of reinforcement learning rules and limited evidence of other forms of supervised learning. Behaviorally associating a stimulus with reinforcement leads to a strengthening of cortical response strength and enlarging of response area with poor selectivity. Associating a stimulus with omission of reinforcement leads to a selective weakening of responses. In some preparations in which these associations are not as clearly made, neurons with the most informative discharges are relatively stronger after training. Studies analyzing the temporal profile of responses associated with omission of reward, or of plasticity in studies with different discriminanda but statistically matched stimuli, support the existence of limited supervised network learning. © 2017 American Physiological Society. Compr Physiol 7:977-1008, 2017.

ASP: Learning to Forget With Adaptive Synaptic Plasticity in Spiking Neural Networks

A fundamental feature of learning in animals is the "ability to forget" that allows an organism to perceive, model and make decisions from disparate streams of information and adapt to changing environments. Against this backdrop, we present a novel unsupervised learning mechanism ASP (Adaptive Synaptic Plasticity) for improved recognition with Spiking Neural Networks (SNNs) for real time on-line learning in a dynamic environment. We incorporate an adaptive weight decay mechanism with the traditional Spike Timing Dependent Plasticity (STDP) learning to model adaptivity in SNNs. The leak rate of the synaptic weights is modulated based on the temporal correlation between the spiking patterns of the pre- and post-synaptic neurons. This mechanism helps in gradual forgetting of insignificant data while retaining significant, yet old, information. ASP, thus, maintains a balance between forgetting and immediate learning to construct a stable-plastic self-adaptive SNN for continuously changing inputs. We demonstrate that the proposed learning methodology addresses catastrophic forgetting while yielding significantly improved accuracy over the conventional STDP learning method for digit recognition applications. Additionally, we observe that the proposed learning model automatically encodes selective attention towards relevant features in the input data while eliminating the influence of background noise (or denoising) further improving the robustness of the ASP learning.

Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

Internet traffic classification based on flows' statistical properties with machine learning

SummaryMachine learning has recently entered the area of network traffic classification as an alternative to the deep packet inspection technique. It provides both unsupervised and supervised learning algorithms that are capable to put aside similar types of traffic or recognize Internet protocols based on some training, pre‐labeled samples. The current work proposes a new approach in the area of network traffic classification using machine learning. First, we extract the unidirectional and bidirectional flows from a traffic capture. A flow is a collection of packets that share sender and receiver IP address and port. Second, we select relevant statistical properties of these flows and use an unsupervised learning mechanism to group flows into clusters based on the similarities. Eventually, we use this classification as training input for a supervised learning engine that will have to properly determine the class of new, unseen traffic flows. Copyright © 2016 John Wiley & Sons, Ltd.

A novel Supervised Competitive Learning algorithm

Competitive learning is a mechanism well-suited for the learning paradigm of regularity detection, and is typically an unsupervised learning mechanism. However, in this work, a novel Supervised Competitive Learning (SCL) algorithm is proposed for the generation of Multiple Classifier Systems (MCSs), which is substantially supervised. SCL algorithm seeks to strengthen simultaneously both the accuracy of and the diversity among the base classifiers in the MCSs, in a supervised and competitive manner. Our inspiration for the development of SCL algorithm comes from the modern education concept and those classical competitive learning algorithms intuitively. It is found through the experimental study of this work that, SCL algorithm effectively improves the classification and generalization performance of the constructed MCSs.

Unsupervised Incremental Learning of Associative Cubes with Orthogonal Kernels

An 'associative cube', a class of auto-associative memories, is revisited here, in which training data and hidden orthogonal basis functions such as wavelet packets or Fourier kernels, are combined in the weight cube. This weight cube has hidden units in its depth, represented by a three dimensional cubic structure. We develop an unsupervised incremental learning mechanism based upon the adaptive least squares method. Training data are mapped into orthogonal basis vectors in a least-squares sense by updating the weights which minimize an energy function. Therefore, a prescribed orthogonal kernel is incrementally assigned to an incoming data. Next, we show how a decoding procedure finds the closest one with a competitive network in the hidden layer. As noisy test data are applied to an associative cube, the nearest one among the original training data are restored in an optimal sense. The simulation results confirm robustness of associative cubes even if test data are heavily distorted by various types of noise.

A continuous-time neural model for sequential action.

Action selection, planning and execution are continuous processes that evolve over time, responding to perceptual feedback as well as evolving top-down constraints. Existing models of routine sequential action (e.g. coffee- or pancake-making) generally fall into one of two classes: hierarchical models that include hand-built task representations, or heterarchical models that must learn to represent hierarchy via temporal context, but thus far lack goal-orientedness. We present a biologically motivated model of the latter class that, because it is situated in the Leabra neural architecture, affords an opportunity to include both unsupervised and goal-directed learning mechanisms. Moreover, we embed this neurocomputational model in the theoretical framework of the theory of event coding (TEC), which posits that actions and perceptions share a common representation with bidirectional associations between the two. Thus, in this view, not only does perception select actions (along with task context), but actions are also used to generate perceptions (i.e. intended effects). We propose a neural model that implements TEC to carry out sequential action control in hierarchically structured tasks such as coffee-making. Unlike traditional feedforward discrete-time neural network models, which use static percepts to generate static outputs, our biological model accepts continuous-time inputs and likewise generates non-stationary outputs, making short-timescale dynamic predictions.

Incrementally learning objects by touch: online discriminative and generative models for tactile-based recognition.

Human beings not only possess the remarkable ability to distinguish objects through tactile feedback but are further able to improve upon recognition competence through experience. In this work, we explore tactile-based object recognition with learners capable of incremental learning. Using the sparse online infinite Echo-State Gaussian process (OIESGP), we propose and compare two novel discriminative and generative tactile learners that produce probability distributions over objects during object grasping/palpation.To enable iterative improvement, our online methods incorporate training samples as they become available. We also describe incremental unsupervised learning mechanisms, based on novelty scores and extreme value theory, when teacher labels are not available. We present experimental results for both supervised and unsupervised learning tasks using the iCub humanoid, with tactile sensors on its five-fingered anthropomorphic hand, and 10 different object classes. Our classifiers perform comparably to state-of-the-art methods (C4.5 and SVM classifiers) and findings indicate that tactile signals are highly relevant for making accurate object classifications. We also show that accurate "early" classifications are possible using only 20-30 percent of the grasp sequence.For unsupervised learning, our methods generate high quality clusterings relative to the widely-used sequential k-means and self-organising map (SOM), and we present analyses into the differences between the approaches.

A cortex-like learning machine for temporal hierarchical pattern clustering, detection, and recognition

A learning machine, called a clustering interpreting probabilistic associative memory (CIPAM), is proposed. CIPAM consists of a clusterer and an interpreter. The clusterer is a recurrent hierarchical neural network of unsupervised processing units (UPUs). The interpreter is a number of supervised processing units (SPUs) that branch out from the clusterer. Each processing unit (PU), UPU or SPU, comprises “dendritic encoders” for encoding inputs to the PU, “synapses” for storing resultant codes, a “nonspiking neuron” for generating inhibitory graded signals to modulate neighboring spiking neurons, “spiking neurons” for computing the subjective probability distribution (SPD) or the membership function, in the sense of fuzzy logic, of the label of said inputs to the PU and generating spike trains with the SPD or membership function as the firing rates, and a masking matrix for maximizing generalization. While UPUs employ unsupervised covariance learning mechanisms, SPUs employ supervised ones. They both also have unsupervised accumulation learning mechanisms. The clusterer of CIPAM clusters temporal and spatial data. The interpreter interprets the resultant clusters, effecting detection and recognition of temporal and hierarchical causes.

A Low-Order Model of Biological Neural Networks

A biologically plausible low-order model (LOM) of biological neural networks is proposed. LOM is a recurrent hierarchical network of models of dendritic nodes and trees; spiking and nonspiking neurons; unsupervised, supervised covariance and accumulative learning mechanisms; feedback connections; and a scheme for maximal generalization. These component models are motivated and necessitated by making LOM learn and retrieve easily without differentiation, optimization, or iteration, and cluster, detect, and recognize multiple and hierarchical corrupted, distorted, and occluded temporal and spatial patterns. Four models of dendritic nodes are given that are all described as a hyperbolic polynomial that acts like an exclusive-OR logic gate when the model dendritic nodes input two binary digits. A model dendritic encoder that is a network of model dendritic nodes encodes its inputs such that the resultant codes have an orthogonality property. Such codes are stored in synapses by unsupervised covariance learning, supervised covariance learning, or unsupervised accumulative learning, depending on the type of postsynaptic neuron. A masking matrix for a dendritic tree, whose upper part comprises model dendritic encoders, enables maximal generalization on corrupted, distorted, and occluded data. It is a mathematical organization and idealization of dendritic trees with overlapped and nested input vectors. A model nonspiking neuron transmits inhibitory graded signals to modulate its neighboring model spiking neurons. Model spiking neurons evaluate the subjective probability distribution (SPD) of the labels of the inputs to model dendritic encoders and generate spike trains with such SPDs as firing rates. Feedback connections from the same or higher layers with different numbers of unit-delay devices reflect different signal traveling times, enabling LOM to fully utilize temporally and spatially associated information. Biological plausibility of the component models is discussed. Numerical examples are given to demonstrate how LOM operates in retrieving, generalizing, and unsupervised and supervised learning.

Functional model of biological neural networks

A functional model of biological neural networks, called temporal hierarchical probabilistic associative memory (THPAM), is proposed in this paper. THPAM comprises functional models of dendritic trees for encoding inputs to neurons, a first type of neuron for generating spike trains, a second type of neuron for generating graded signals to modulate neurons of the first type, supervised and unsupervised Hebbian learning mechanisms for easy learning and retrieving, an arrangement of dendritic trees for maximizing generalization, hardwiring for rotation-translation-scaling invariance, and feedback connections with different delay durations for neurons to make full use of present and past informations generated by neurons in the same and higher layers. These functional models and their processing operations have many functions of biological neural networks that have not been achieved by other models in the open literature and provide logically coherent answers to many long-standing neuroscientific questions. However, biological justifications of these functional models and their processing operations are required for THPAM to qualify as a macroscopic model (or low-order approximate) of biological neural networks.

A Model of Indispensability of a Large Glial Layer in Cerebrovascular Circulation

We formulate the problem of oxygen delivery to neural tissue as a problem of association. Input to a pool of neurons in one brain area must be matched in space and time with metabolic inputs from the vascular network via the glial network. We thus have a model in which neural, glial, and vascular layers are connected bidirectionally, in that order. Connections between neuro-glial and glial-vascular stages are trained by an unsupervised learning mechanism such that input to the neural layer is sustained by the precisely patterned delivery of metabolic inputs from the vascular layer via the glial layer. Simulations show that the capacity of such a system to sustain patterns is weak when the glial layer is absent. Capacity is higher when a glial layer is present and increases with the layer size. The proposed formulation of neurovascular interactions raises many intriguing questions about the role of glial cells in cerebral circulation.

Emerging Cooperation With Minimal Effort: Rewarding Over Mimicking

This paper compares supervised and unsupervised learning mechanisms for the emergence of cooperative multiagent spatial coordination using a top-down approach. By observing the global performance of a group of homogeneous agents-supported by a nonglobal knowledge of their environment-we attempt to extract information about the minimum size of the agent neurocontroller and the type of learning mechanism that collectively generate high-performing and robust behaviors with minimal computational effort. Consequently, a methodology for obtaining controllers of minimal size is introduced and a comparative study between supervised and unsupervised learning mechanisms for the generation of successful collective behaviors is presented. We have developed a prototype simulated world for our studies. This case study is primarily a computer games inspired world but its main features are also biologically plausible. The two specific tasks that the agents are tested in are the competing strategies of obstacle-avoidance and target-achievement. We demonstrate that cooperative behavior among agents, which is supported only by limited communication, appears to be necessary for the problem's efficient solution and that learning by rewarding the behavior of agent groups constitutes a more efficient and computationally preferred generic approach than supervised learning approaches in such complex multiagent worlds

An incremental network for on-line unsupervised classification and topology learning

This paper presents an on-line unsupervised learning mechanism for unlabeled data that are polluted by noise. Using a similarity threshold-based and a local error-based insertion criterion, the system is able to grow incrementally and to accommodate input patterns of on-line non-stationary data distribution. A definition of a utility parameter, the error-radius, allows this system to learn the number of nodes needed to solve a task. The use of a new technique for removing nodes in low probability density regions can separate clusters with low-density overlaps and dynamically eliminate noise in the input data. The design of two-layer neural network enables this system to represent the topological structure of unsupervised on-line data, report the reasonable number of clusters, and give typical prototype patterns of every cluster without prior conditions such as a suitable number of nodes or a good initial codebook.

Clustering of diverse genomic data using information fusion

Genome sequencing projects and high-through-put technologies like DNA and Protein arrays have resulted in a very large amount of information-rich data. Microarray experimental data are a valuable, but limited source for inferring gene regulation mechanisms on a genomic scale. Additional information such as promoter sequences of genes/DNA binding motifs, gene ontologies, and location data, when combined with gene expression analysis can increase the statistical significance of the finding. This paper introduces a machine learning approach to information fusion for combining heterogeneous genomic data. The algorithm uses an unsupervised joint learning mechanism that identifies clusters of genes using the combined data. The correlation between gene expression time-series patterns obtained from different experimental conditions and the presence of several distinct and repeated motifs in their upstream sequences is examined here using publicly available yeast cell-cycle data. The results show that the combined learning approach taken here identifies correlated genes effectively. The algorithm provides an automated clustering method, but allows the user to specify apriori the influence of each data type on the final clustering using probabilities. Software code is available by request from the first author. jkasturi@cse.psu.edu.

Spontaneous muscle twitches during sleep guide spinal self-organization.

During development, information about the three-dimensional shape and mechanical properties of the body is laid down in the synaptic connectivity of sensorimotor systems through unknown adaptive mechanisms. In spinal reflex systems, this enables the fast transformation of complex sensory information into adequate correction of movements. Here we use a computer simulation to show that an unsupervised correlation-based learning mechanism, using spontaneous muscle twitches, can account for the functional adaptation of the withdrawal reflex system. We also show that tactile feedback resulting from spontaneous muscle twitches during sleep does indeed modify sensorimotor transformation in young rats in a predictable manner. The results indicate that these twitches, corresponding to human fetal movements, are important in spinal self-organization.

Self-organization of spiking neurons using action potential timing

We propose a mechanism for unsupervised learning in networks of spiking neurons which is based on the timing of single firing events. Our results show that a topology preserving behavior quite similar to that of Kohonen's self-organizing map can be achieved using temporal coding. In contrast to previous approaches, which use rate coding, the winner among competing neurons can be determined fast and locally. Our model is a further step toward a more realistic description of unsupervised learning in biological neural systems. Furthermore, it may provide a basis for fast implementations in pulsed VLSI (very large scale integration).

Improvement in line orientation discrimination is retinally local but dependent on cognitive set.

The ability of human observers to discriminate the orientation of a pair of straight lines differing by 3 degrees improved with practice. The improvement did not transfer across hemifield or across quadrants within the same hemifield. The practice effect occurred whether or not observers were given feedback. However, orientation discrimination did not improve when observers attended to brightness rather than orientation of the lines. This suggests that cognitive set affects tuning in retinally local orientation channels (perhaps by guiding some form of unsupervised learning mechanism) and that retinotopic feature extraction may not be wholly preattentive.