Unsupervised Learning Mechanism Research Articles

Neuroscientific insights about computer vision models: a concise review.

The development of biologically-inspired computational models has been the focus of study ever since the artificial neuron was introduced by McCulloch and Pitts in 1943. However, a scrutiny of literature reveals that most attempts to replicate the highly efficient and complex biological visual system have been futile or have met with limited success. The recent state-of the-art computer vision models, such as pre-trained deep neural networks and vision transformers, may not be biologically inspired per se. Nevertheless, certain aspects of biological vision are still found embedded, knowingly or unknowingly, in the architecture and functioning of these models. This paper explores several principles related to visual neuroscience and the biological visual pathway that resonate, in some manner, in the architectural design and functioning of contemporary computer vision models. The findings of this survey can provide useful insights for building futuristic bio-inspired computer vision models. The survey is conducted from a historical perspective, tracing the biological connections of computer vision models starting with the basic artificial neuron to modern technologies such as deep convolutional neural network (CNN) and spiking neural networks (SNN). One spotlight of the survey is a discussion on biologically plausible neural networks and bio-inspired unsupervised learning mechanisms adapted for computer vision tasks in recent times.

Tennis teaching assistance model based on double chain shared unsupervised action recognition algorithm

The traditional self-supervised methods based on skeleton data frequently categorize the various enhancements of a given sample as positive examples, while the remaining samples are designated as negative examples. This approach results in a significant imbalance in the ratio of positive to negative samples, which in turn constrains the efficacy of samples with identical semantic information. Therefore, to further improve the training quality in tennis teaching and enhance the accuracy of action recognition, a dual chain sharing unsupervised action recognition algorithm has been proposed. This study first designs a skeleton topology data augmentation method based on the physical connections of human joints to obtain advanced semantic embeddings. Then, an improved positive sample expansion strategy is utilized to enhance the diversity and quality of training data. Next, an unsupervised learning mechanism is employed to autonomously learn and recognize complex patterns of tennis movements. To measure the performance of the model, tests were conducted on its accuracy, F1 score, recognition time, and fitting degree. The experimental results showed that the proposed algorithm could reach its optimal state after 23 iterations of training, and its F1 value reached 0.918, with an average accuracy of 92.9 % and an average recognition time of 7.4 s. The research algorithms were superior to the multi-input branch graph convolutional network action recognition algorithms used for comparison, pull-push contrastive loss action recognition algorithms, and multi-granularity anchor contrastive representation learning action recognition algorithms. Its accuracy was leading by 8.6 %-23.5 %, and the recognition time has been reduced by 2.3s-7.4 s. In addition, in terms of the fitting degree of action recognition, compared with other methods, the proposed method had a fitting degree of up to 95.7 %, which was at least 8.1 % higher. This research method can improve the timeliness of feedback from trainers by accurately and quickly recognizing movements, helping coaches develop more targeted training plans, thereby improving the efficiency and quality of tennis teaching.

A neural network model of differentiation and integration of competing memories.

What determines when neural representations of memories move together (integrate) or apart (differentiate)? Classic supervised learning models posit that, when two stimuli predict similar outcomes, their representations should integrate. However, these models have recently been challenged by studies showing that pairing two stimuli with a shared associate can sometimes cause differentiation, depending on the parameters of the study and the brain region being examined. Here, we provide a purely unsupervised neural network model that can explain these and other related findings. The model can exhibit integration or differentiation depending on the amount of activity allowed to spread to competitors - inactive memories are not modified, connections to moderately active competitors are weakened (leading to differentiation), and connections to highly active competitors are strengthened (leading to integration). The model also makes several novel predictions - most importantly, that when differentiation occurs as a result of this unsupervised learning mechanism, it will be rapid and asymmetric, and it will give rise to anticorrelated representations in the region of the brain that is the source of the differentiation. Overall, these modeling results provide a computational explanation for a diverse set of seemingly contradictory empirical findings in the memory literature, as well as new insights into the dynamics at play during learning.

A neural network model of differentiation and integration of competing memories

What determines when neural representations of memories move together (integrate) or apart (differentiate)? Classic supervised learning models posit that, when two stimuli predict similar outcomes, their representations should integrate. However, these models have recently been challenged by studies showing that pairing two stimuli with a shared associate can sometimes cause differentiation, depending on the parameters of the study and the brain region being examined. Here, we provide a purely unsupervised neural network model that can explain these and other related findings. The model can exhibit integration or differentiation depending on the amount of activity allowed to spread to competitors — inactive memories are not modified, connections to moderately active competitors are weakened (leading to differentiation), and connections to highly active competitors are strengthened (leading to integration). The model also makes several novel predictions — most importantly, that when differentiation occurs as a result of this unsupervised learning mechanism, it will be rapid and asymmetric, and it will give rise to anticorrelated representations in the region of the brain that is the source of the differentiation. Overall, these modeling results provide a computational explanation for a diverse set of seemingly contradictory empirical findings in the memory literature, as well as new insights into the dynamics at play during learning.

Ualign: pushing the limit of template-free retrosynthesis prediction with unsupervised SMILES alignment

MotivationRetrosynthesis planning poses a formidable challenge in the organic chemical industry, particularly in pharmaceuticals. Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recent years due to advancements in AI for science. Various deep learning-based methods have been proposed for this task in recent years, incorporating diverse levels of additional chemical knowledge dependency.ResultsThis paper introduces UAlign, a template-free graph-to-sequence pipeline for retrosynthesis prediction. By combining graph neural networks and Transformers, our method can more effectively leverage the inherent graph structure of molecules. Based on the fact that the majority of molecule structures remain unchanged during a chemical reaction, we propose a simple yet effective SMILES alignment technique to facilitate the reuse of unchanged structures for reactant generation. Extensive experiments show that our method substantially outperforms state-of-the-art template-free and semi-template-based approaches. Importantly, our template-free method achieves effectiveness comparable to, or even surpasses, established powerful template-based methods.Scientific contributionWe present a novel graph-to-sequence template-free retrosynthesis prediction pipeline that overcomes the limitations of Transformer-based methods in molecular representation learning and insufficient utilization of chemical information. We propose an unsupervised learning mechanism for establishing product-atom correspondence with reactant SMILES tokens, achieving even better results than supervised SMILES alignment methods. Extensive experiments demonstrate that UAlign significantly outperforms state-of-the-art template-free methods and rivals or surpasses template-based approaches, with up to 5% (top-5) and 5.4% (top-10) increased accuracy over the strongest baseline.

Tunable spike-timing-dependent plasticity in magnetic skyrmion manipulation chambers

Magnetic skyrmions, as scalable and nonvolatile spin textures, can dynamically interact with fields and currents, making them promising for unconventional computing. This paper presents a neuromorphic device based on skyrmion manipulation chambers to implement spike-timing-dependent plasticity (STDP), a mechanism for unsupervised learning in brain-inspired computing. STDP adjusts synaptic weights based on the timing of pre-synaptic and post-synaptic spikes. The proposed three-chamber design encodes synaptic weight in the number of skyrmions in the center chamber, with left and right chambers for pre- and post-synaptic spikes, respectively. Micromagnetic simulations demonstrate that the timing between applied currents across the chambers controls the final skyrmion count (weight). The device exhibits adaptability and learning capabilities by manipulating chamber parameters, mimicking Hebbian and dendritic location-based plasticity. The device's ability to maintain state post-write highlights its potential for advancing adaptable neuromorphic devices.

Deep unsupervised learning using spike-timing-dependent plasticity

Spike-timing-dependent plasticity (STDP) is an unsupervised learning mechanism for spiking neural networks that has received significant attention from the neuromorphic hardware community. However, scaling such local learning techniques to deeper networks and large-scale tasks has remained elusive. In this work, we investigate a Deep-STDP framework where a rate-based convolutional network, that can be deployed in a neuromorphic setting, is trained in tandem with pseudo-labels generated by the STDP clustering process on the network outputs. We achieve 24.56% higher accuracy and 3.5 × faster convergence speed at iso-accuracy on a 10-class subset of the Tiny ImageNet dataset in contrast to a k-means clustering approach.

A novel breast cancer image classification model based on multiscale texture feature analysis and dynamic learning

Assistive medical image classifiers can greatly reduce the workload of medical personnel. However, traditional machine learning methods require large amounts of well-labeled data and long learning times to solve medical image classification problems, which can lead to high training costs and poor applicability. To address this problem, a novel unsupervised breast cancer image classification model based on multiscale texture analysis and a dynamic learning strategy for mammograms is proposed in this paper. First, a gray-level cooccurrence matrix and Tamura coarseness are used to transfer images to multiscale texture feature vectors. Then, an unsupervised dynamic learning mechanism is used to classify these vectors. In the simulation experiments with a resolution of 40 pixels, the accuracy, precision, F1-score and AUC of the proposed method reach 91.500%, 92.780%, 91.370%, and 91.500%, respectively. The experimental results show that the proposed method can provide an effective reference for breast cancer diagnosis.

Unsupervised learning of perceptual feature combinations.

In many situations it is behaviorally relevant for an animal to respond to co-occurrences of perceptual, possibly polymodal features, while these features alone may have no importance. Thus, it is crucial for animals to learn such feature combinations in spite of the fact that they may occur with variable intensity and occurrence frequency. Here, we present a novel unsupervised learning mechanism that is largely independent of these contingencies and allows neurons in a network to achieve specificity for different feature combinations. This is achieved by a novel correlation-based (Hebbian) learning rule, which allows for linear weight growth and which is combined with a mechanism for gradually reducing the learning rate as soon as the neuron's response becomes feature combination specific. In a set of control experiments, we show that other existing advanced learning rules cannot satisfactorily form ordered multi-feature representations. In addition, we show that networks, which use this type of learning always stabilize and converge to subsets of neurons with different feature-combination specificity. Neurons with this property may, thus, serve as an initial stage for the processing of ecologically relevant real world situations for an animal.

Bridge progressive damage detection using unsupervised learning and self-attention mechanism

This paper presents a novel unsupervised method for detecting progressive damage in bridge structures. Traditional supervised learning approaches require a large number of damaged samples to train a high-performing detection model, which poses challenges when applied to normal in-service bridges. Since in-service bridges usually lack data from damage scenarios and existing methods fail to achieve real-time detection, unsupervised learning has gained popularity due to its ability to work without damaged samples and offer better real-time performance. In light of this, this paper proposes a novel unsupervised damage detection method that utilizes an unsupervised attention-convolutional auto-encoder to reconstruct real-time vibration signals from bridge. Two damage indicators are employed to evaluate the effectiveness of the reconstruction process, aiming to capture potential changes in the progressive damage of bridges. The results demonstrate that: the attention-convolutional auto-encoder achieves excellent reconstruction performance for vibration signals from intact structures, which reconstruction error converging to 0 and structural similarity approaching 1. However, the reconstruction performance is less satisfactory for vibration signals in damage scenarios, deteriorating further as the damage level increases. By analyzing the variation patterns of vibration signals in attention-convolutional auto-encoders, it was confirmed that the reliability of the proposed evaluation effects by the two different types of damage indicators. Finally, the trend of progressive damage was extracted through these indicators, showcasing the effectiveness of the method in detecting progressive damage. This approach facilitates the identification of potential progressive changes in the normal operation process of bridges, thus enhancing real-time damage detection capabilities and contributing to the knowledge of bridge monitoring.

Threshold plasticity of SOI-GST microring resonators.

Spiking Neural Networks, also known as third generation Artificial Neural Networks, have widely attracted more attention because of their advantages of behaving more biologically interpretable and being more suitable for hardware implementation. Apart from using traditional synaptic plasticity, neural networks can also be based on threshold plasticity, achieving similar functionality. This can be implemented using e.g. the Bienenstock, Cooper and Munro rule. This is a classical unsupervised learning mechanism in which the threshold is closely related to the output of the post-synaptic neuron. We show in simulations that the threshold characteristics of the nonlinear effects of a microring resonator integrated with Ge2Sb2Te5 demonstrate some complex dependencies on the intracavity refractive index, attenuation, and wavelength detuning of the incident optical pulse, and exhibit class II excitability. We also show that we are able to modify the threshold power of the microring resonator by the changes of the refractive index and loss of Ge2Sb2Te5, due to transitions between the crystalline and amorphous states. Simulations show that the presented device exhibits both excitatory and inhibitory learning behavior, either lowering or raising the threshold.

Predictive Precoder Design for OTFS-Enabled URLLC: A Deep Learning Approach

This paper investigates the orthogonal time frequency space (OTFS) transmission for enabling ultra-reliable low-latency communications (URLLC). To guarantee excellent reliability performance, pragmatic precoder design is an effective and indispensable solution. However, the design requires accurate instantaneous channel state information at the transmitter (ICSIT) which is not always available in practice. Motivated by this, we adopt a deep learning (DL) approach to exploit implicit features from estimated historical delay-Doppler domain channels (DDCs) to directly predict the precoder to be adopted in the next time frame for minimizing the frame error rate (FER), that can further improve the system reliability without the acquisition of ICSIT. To this end, we first establish a predictive transmission protocol and formulate a general problem for the precoder design where a closed-form theoretical FER expression is derived serving as the objective function to characterize the system reliability. Then, we propose a DL-based predictive precoder design framework which exploits an unsupervised learning mechanism to improve the practicability of the proposed scheme. As a realization of the proposed framework, we design a DDCs-aware convolutional long short-term memory (CLSTM) network for the precoder design, where both the convolutional neural network and LSTM modules are adopted to facilitate the spatial-temporal feature extraction from the estimated historical DDCs to further enhance the precoder performance. Simulation results demonstrate that the proposed scheme facilitates a flexible reliability-latency tradeoff and achieves an excellent FER performance that approaches the lower bound obtained by a genie-aided benchmark requiring perfect ICSI at both the transmitter and receiver.

Unsupervised machine learning based key management in wireless sensor networks

In distributed sensor applications, the secured infrastructure plays a major role in processing and transmission of data. The data transfer in wireless sensor network (WSN) is equipped security measure that prevents the manipulation of data theft by the attackers. The key management protocol offers secured delivery of messages that includes integrity and authenticity via key generation, key distribution and maintenance. In this paper, we develop a lightweight key management protocol (LKMP) that involves reduced memory consumption and processing power. The study uses machine learning algorithm for key management in WSN, and the machine learning uses unsupervised learning mechanism. The simulation is conducted in network simulator and it is compared with existing state-of-the-art models. The results of simulation shows that the proposed method achieves higher rate of throughput, security and resilience than its predecessors.

Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention Mechanism

Since light propagation in water bodies is subject to absorption and scattering effects, underwater images using only conventional intensity cameras will suffer from low brightness, blurred images, and loss of details. In this paper, a deep fusion network is applied to underwater polarization images; that is, the underwater polarization images are fused with intensity images using the deep learning method. To construct a training dataset, we establish an experimental setup to obtain underwater polarization images and perform appropriate transformations to expand the dataset. Next, an end-to-end learning framework based on unsupervised learning and guided by an attention mechanism is constructed for fusing polarization and light intensity images. The loss function and weight parameters are elaborated. The produced dataset is used to train the network under different loss weight parameters, and the fused images are evaluated based on different image evaluation metrics. The results show that the fused underwater images are more detailed. Compared with light intensity images, the information entropy and standard deviation of the proposed method increase by 24.48% and 139%. The image processing results are better than other fusion-based methods. In addition, the improved U-net network structure is used to extract features for image segmentation. The results show that the target segmentation based on the proposed method is feasible under turbid water. The proposed method does not require manual adjustment of weight parameters, has faster operation speed, and has strong robustness and self-adaptability, which is important for research in vision fields, such as ocean detection and underwater target recognition.

Research on Curriculum Design Method of Teaching Resource Library based on Deep Learning Technology

In order to improve the ideological understanding of computer majors and establish a correct world outlook, outlook on life and values, the ideological and political goals of computer majors are designed; (1) A new deep learning face recognition algorithm is proposed. Aiming at the limitations of many current methods of artificially designing image description features, this algorithm proposes an unsupervised big data-driven deep image feature learning and representation mechanism. (2) A new idea of single-target tracking algorithm DPL is proposed. Single target tracking is a hot research topic in the field of computer anxiety. Our proposed DPL algorithm is still very competitive with the best algorithms in the field of object tracking. Several key technology research and model design schemes for computer major courses are proposed, which enriches the relevant research content of deep learning in the field of computer vision, and has certain theoretical and practical significance.

Application Development for Customer Segmentation Using an Unsupervised Learning Algorithm

Making wise selections is a requirement for any business to produce healthy revenue. Every customer in a firm is unique in comparison to other possible customers, and each one has various preferences for and objections to the product. The clients are divided into groups based on shared traits including gender, age, interests, and spending patterns. Targeting a certain group of customers with specialized goods, services, and marketing methods is made simpler by the customer segmentation process. This study focuses on segmenting customers based on their income and spending scores. The segmentation is done using the KMeans clustering algorithm, an unsupervised learning mechanism, and the total data is divided into three clusters. The model is then implemented using Python and the Flask web framework.

Underwater polarization image fusion based on unsupervised learning and attention mechanisms

Underwater polarization image fusion based on unsupervised learning and attention mechanisms

Graph Spring Network and Informative Anchor Selection for session-based recommendation

Session-based recommendation (SBR) aims at predicting the next item for an ongoing anonymous session. The major challenge of SBR is how to capture richer relations in between items and learn ID-based item embeddings to capture such relations. Recent studies propose to first construct an item graph from sessions and employ a Graph Neural Network (GNN) to encode item embedding from the graph. Although such graph-based approaches have achieved performance improvements, their GNNs are not suitable for ID-based embedding learning for the SBR task. In this paper, we argue that the objective of such ID-based embedding learning is to capture a kind of neighborhood affinity in that the embedding of a node is similar to that of its neighbors’ in the embedding space. We propose a new graph neural network, called Graph Spring Network (GSN), for learning ID-based item embedding on an item graph to optimize neighborhood affinity in the embedding space. Furthermore, we argue that even stacking multiple GNN layers may not be enough to encode potential relations for two item nodes far-apart in a graph. In this paper, we propose a strategy that first selects some informative item anchors and then encode items’ potential relations to such anchors. In summary, we propose a GSN-IAS model (Graph Spring Network and Informative Anchor Selection) for the SBR task. We first construct an item graph to describe items’ co-occurrences in all sessions. We design the GSN for ID-based item embedding learning and propose an item entropy measure to select informative anchors. We then design an unsupervised learning mechanism to encode items’ relations to anchors. We next employ a shared gated recurrent unit (GRU) network to learn two session representations and make two next item predictions. Finally, we design an adaptive decision fusion strategy to fuse two predictions to make the final recommendation. Extensive experiments on three public datasets demonstrate the superiority of our GSN-IAS model over the state-of-the-art models.

Using habituation as a simple and fundamental learning mechanism in an embodied artificial agent

Habituation, a non-associative learning widely observed across phylogeny, is fundamental for adaptation and, thus, survival of living organisms. This paper investigates the main characteristics of habituation in order to present three new computational models inspired by habituation. We develop these models as part of the Iterant Deformable Sensorimotor Medium (IDSM), a recently developed abstract model of behavior formation. The characteristics of these models are studied and analyzed. Our long-term objective is to research new unsupervised learning mechanisms for artificial learning agents.

Combining Unsupervised and Supervised Learning for Sample Efficient Continuous Language Grounding

Natural and efficient communication with humans requires artificial agents that are able to understand the meaning of natural language. However, understanding natural language is non-trivial and requires proper grounding mechanisms to create links between words and corresponding perceptual information. Since the introduction of the “Symbol Grounding Problem” in 1990, many different grounding approaches have been proposed that either employed supervised or unsupervised learning mechanisms. The latter have the advantage that no other agent is required to learn the correct groundings, while the former are often more sample-efficient and accurate but require the support of another agent, like a human or another artificial agent. Although combining both paradigms seems natural, it has not achieved much attention. Therefore, this paper proposes a hybrid grounding framework which combines both learning paradigms so that it is able to utilize support from a tutor, if available, while it can still learn when no support is provided. Additionally, the framework has been designed to learn in a continuous and open-ended manner so that no explicit training phase is required. The proposed framework is evaluated through two different grounding scenarios and its unsupervised grounding component is compared to a state-of-the-art unsupervised Bayesian grounding framework, while the benefit of combining both paradigms is evaluated through the analysis of different feedback rates. The obtained results show that the employed unsupervised grounding mechanism outperforms the baseline in terms of accuracy, transparency, and deployability and that combining both paradigms increases both the sample-efficiency as well as the accuracy of purely unsupervised grounding, while it ensures that the framework is still able to learn the correct mappings, when no supervision is available.