Divergence Algorithm Research Articles

Efficient training of energy-based models using Jarzynski equality**This article is an updated version of: Carbone D, Hua M, Coste S and Vanden-Eijnden E 2023 Efficient training of energy-based models using Jarzynski equality Advances in Neural Information Processing Systems vol 36, ed A Oh, T Naumann, A Globerson, K Saenko, M Hardt and S Levine (Curran Associates, Inc.) pp 52583–614.

Abstract Energy-based models (EBMs) are generative models inspired by statistical physics with a wide range of applications in unsupervised learning. Their performance is well measured by the cross-entropy (CE) of the model distribution relative to the data distribution. Using the CE as the objective for training is, however, challenging because the computation of its gradient with respect to the model parameters requires sampling of the model distribution. Here, we show how the results for nonequilibrium thermodynamics based on the Jarzynski equality together with tools from sequential Monte Carlo sampling can be used to perform this computation efficiently and avoid the uncontrolled approximations made using the standard contrastive divergence algorithm. Specifically, we introduce a modification of the unadjusted Langevin algorithm (ULA), in which each walker acquires a weight that enables the estimation of the gradient of the CE at any step during gradient descent, thereby bypassing sampling biases induced by slow mixing of the ULA. We illustrate these results with numerical experiments on Gaussian mixture distributions as well as the MNIST and CIFAR-10 datasets. We show that the proposed approach outperforms methods based on the contrastive divergence algorithm in all the considered situations.

A Study on Network Anomaly Detection Using Fast Persistent Contrastive Divergence

As network technology evolves, cyberattacks are not only increasing in frequency but also becoming more sophisticated. To proactively detect and prevent these cyberattacks, researchers are developing intrusion detection systems (IDSs) leveraging machine learning and deep learning techniques. However, a significant challenge with these advanced models is the increased training time as model complexity grows, and the symmetry between performance and training time must be taken into account. To address this issue, this study proposes a fast-persistent-contrastive-divergence-based deep belief network (FPCD-DBN) that offers both high accuracy and rapid training times. This model combines the efficiency of contrastive divergence with the powerful feature extraction capabilities of deep belief networks. While traditional deep belief networks use a contrastive divergence (CD) algorithm, the FPCD algorithm improves the performance of the model by passing the results of each detection layer to the next layer. In addition, the mix of parameter updates using fast weights and continuous chains makes the model fast and accurate. The performance of the proposed FPCD-DBN model was evaluated on several benchmark datasets, including NSL-KDD, UNSW-NB15, and CIC-IDS-2017. As a result, the proposed method proved to be a viable solution as the model performed well with an accuracy of 89.4% and an F1 score of 89.7%. By achieving superior performance across multiple datasets, the approach shows great potential for enhancing network security and providing a robust defense against evolving cyber threats.

Learning restricted Boltzmann machines with pattern induced weights

Restricted Boltzmann Machines are energy-based models capable of learning probability distributions. In practice, though, it is seriously limited by the fact that the computational cost associated with the exact evaluation of the gradients, required during learning, is prohibitively high. The standard approach to mitigate this problem is to use the Contrastive Divergence algorithm, but it leads to a rough approximation that presents issues on its own. As a completely different alternative, a model called RAPID (Pozas-Kerstjen et al., 2021) recently appeared, where unit weights are constructed from high-probability patterns that allow for an effective evaluation of the update rules along learning. In this work we analyze RAPID to find that it also presents some drawbacks that constrain its performance. We identify the problematic sources in RAPID and modify them accordingly to build a similar but more flexible alternative, called PIW (Pattern Induced Weights). Experiments show that PIW performs better than the original RAPID implementation, bringing it to a competitive level when compared to a standard RBM with CDk, with a substantial reduction in the number of training parameters.

Potentials of spaceborne imaging spectrometer PRISMA, ASTER, and ALOS-1 PALSAR datasets for mineral mapping and geological controls of mineral deposit in Jahazpur, Rajasthan, India

Palaeoproterozoic rocks of the Jahazpur region are well known for talc mineralization and its mining. The present study attempts to identify and map the talc and associated minerals and their structural control using multi-source remote sensing datasets. Remote Sensing studies were carried out using the relative band depth methods for the ASTER dataset for mapping talc and other associated minerals of the region. Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Minimum Noise Fraction (MNF) were applied to the PRISMA dataset to map the lithology of the region. Along with that, the Spectral Angle Mapper (SAM) and Spectral Information Divergence (SID) algorithms map the talc and clay minerals using the PRISMA dataset. ALOS – 1 PALSAR dataset had been utilized to delineate the various lineaments present in the region at different angles. The obtained mineral maps form the ASTER had been validated with results of the PRISMA classified map and showed a good number of similarities. The obtained results from remote sensing have been further validated with the help of field survey and XRD analysis which confirms the presence of talc and clay minerals in the region. The structural pattern of the lineament shows the similarity in the direction orientation with the Jahazpur Thrust. Dolomites and clay minerals were mapped around the talc mining region which suggests that the alteration of these minerals played an important role in the formation of talc. Clay minerals were also mapped there and formed due to the weathering of the granites of Berach and Jahazpur present in the region. Both talc and clay deposits are present at the higher lineament density zones which represents the structural control over the mineralization. Therefore, the mineral deposits of the Jahazpur region are mineralogical and structurally controlled.

Application of Deep Belief Network in Weather Modeling: PM2.5 Concentration in Thailand

In Thailand, the number of particles matter with diameter of less than 2.5 microns or PM2.5 concentration exceed the standard in many areas, especially in Chiang Mai. This affects the image of the country in terms of economy, health, and environment. The objective of this research is to study the structure of model for PM2.5 concentration by using a Deep Belief Network (DBN) with the daily data set of PM2.5 concentration from the air quality monitoring station at Yupparaj Wittayalai School, Chiang Mai. The data was analyzed through an unsupervised path using the Minimizing Contrastive Divergence (MCD) algorithm, followed by a supervised path using Back-Propagation Neural Network (BPNN) algorithm to estimate the parameters of DBN. The result shows that the optimal DBN structure has 5 input nodes and 20 hidden neurons in the first hidden layer. This model has an 88.4 percent accuracy in forecasting PM2.5 concentration. In addition, this model can be applied for other weather forecasting such as rainfall or water level in a basin.

DSPM: Dual sequence prediction model for efficient energy management in micro-grid

Power generation and consumption predictions are fundamental for smart grid operations, addressing challenges posed by renewable energy variability and irregular consumer demand. This study introduces the Dual Sequence Predictive Model (DSPM) based on Spatiotemporal CNN (STCNN) architecture, offering a holistic solution for forecasting Electricity Generation (EG) and Electricity Consumption (EC) collectively. Leveraging STCNN, the DSPM efficiently extracts spatial and temporal information, improving prediction accuracy and processing speed. A 1D spatial attention module is added to capture crucial spatial dependencies in historical data. Incorporating shared historical weather information streamlines learning process and reduces model complexity. Extensive benchmark evaluations demonstrate the DSPM superior performance, achieving the lowest error rates compared to baseline models. The DSPM also employs the Kullback–Leibler Divergence (KLD) algorithm for power generation and consumption matching, ensuring efficient power distribution within smart and microgrids. Furthermore, the DSPM is evaluated alongside Single Sequence Prediction (SSP) models, providing a comprehensive analysis of its capabilities and comparisons with state-of-the-art models. The SSP model achieved an average RMSE reduction of 17.3% for solar EG data and 15.86% for IHEPC residential EC data, while DSPM reduced RMSE by 7.57% over PowerGrid dataset compared to baseline models.

Innovation and Practice of Educational Management System in Colleges and Universities Based on the Concept of Data Analysis Education

Abstract This paper proposes the evaluation method of college education management mode based on deep belief network (DBN), establishes the evaluation index of college education management mode, takes it as the input of the deep belief network, adopts the divergence algorithm and backpropagation algorithm to learn and optimize the parameters of the deep belief network, and establishes the evaluation model of the education management mode of universities. The evaluation method of the college education management model evaluation of the deep belief network is verified by evaluating the results and performing error analysis on 438 questionnaire test samples. The results show that the number of training steps of the adopted DBN model in the supervised tuning stage is 214, and the error fluctuation range is ±0.6, which achieves the expected effect, indicating that the adoption of the model has accuracy in the evaluation of college education management model. Under the concept of data analysis education, the evaluation method proposed in this paper has a positive significance for the innovation and practice of educational and teaching management systems.

A novel lidar signal noise reduction algorithm based on improved deep belief network

To reduce noise in the lidar return signal, an improved deep belief network (DBN) denoising algorithm is proposed in this study. In the traditional implementation process of DBN, a multi-layer fully connected network is realized by stacking restricted Boltzmann machines (RBMs). However, the RBM is an undirected graph model, and there is no clear causal relationship between random variable nodes. The denoising autoencoder (DAE) can avoid this problem and produce field generalization performance by adding random contamination during training and stacking, thereby achieving better performance than the traditional DBN. In this study, a new multi-layer DBN called DADBN is implemented by stacking DAE and RBM. First, the multi-layer DAE is placed in the beginning layer of the network as the primary filter of the signal to provide data dimensionality reduction and feature extraction. Then, the RBM is used as the lower layer, the hidden layer is calculated according to the initial value of the visible layer by the contrast of the divergence algorithm, and the visible layer is reconstructed from the samples of the hidden layer. And the sparse representation penalty is added to the RBM model to solve the assimilation phenomenon of hidden layer nodes in the RBM model. It not only optimizes the log-likelihood function when training data, but also makes the probability of each hidden layer node being activated tend to a minimum value, so as to sparsely activate the sparse hidden layer nodes. The weight matrix W is obtained by computing the results of the hidden layer twice. Finally, the original input signal was reconstructed by Gibbs sampling layer and the reconstructed signal was decoded by the decoder to achieve the purpose of noise reduction. To verify its effectiveness, this method is compared with four other denoising methods: wavelet packet algorithm, complete ensemble empirical modal decomposition (CEEMDAN), wavelet transform and empirical mode decomposition (WT-EMD), and wavelet transform-variational mode decomposition (WT-VMD). The noise reduction effect of DADBN is better than that of the other four methods, thus effectively eliminating complex noise in the lidar detection signal.

3D Buildings Change Detection from Aerial and Satellite Stereo Imagery Using Kullback–Leibler Divergence Algorithm

Monitoring city sprawls is considered an essential subject in urban planning. The most important object in the urban areas is the building; therefore, finding an automatic method for detecting the changes in the buildings is considered a priority task for researchers to consider the changes in a district, especially for assessing the damages during disasters and updating geo-database. However, using 2D images to detect changes is ineffective because of the various imaging environments and the parameters of the sensors. Furthermore, during the change detection process, it is difficult to distinguish between the building and other objects due to the similarity of spectral properties. Therefore, it is necessary to use stereo images for DSM generation and then find the changes. This paper proposes a Kullback–Leibler divergence (KLD) algorithm to detect urban area changes based on stereo imagery. Two DSMs have been obtained through the photogrammetric process using two different sensors. The first data set is based on the stereo aerial imagery captured in 2012 and the second stereo is from the worldview-2 sensor captured in 2017. Before applying the KLD algorithm, the aerial’s DSM, which has an original resolution of 0.3m, was resampled to 1 m to make it similar to the satellite’s DSM. Three study areas have been selected for the algorithms test, located in Erbil-Iraq. The assessment shows that the KLD detected changes better than other methods after removing the small fragments through the post-processing step. For the evaluation, the confusion matrix has been determined for each study area. The analysis demonstrates that the overall accuracy for the three study areas where 89.3%, 91.1% and 88.9 %, respectively.

Coarse-grained RNA simulations with concerted c2'/c3'-endo sugar pucker transitions.

All-atom molecular dynamic simulations are generally restricted by the time scale that can be sampled. To address this issue, various coarse-grained RNA models have been developed. These models often assume the ribose, a 5 membered ring, is fixed in only one conformation, typically the 3’-endo found in A-form helices. The models neglect the 2’-endo conformation that can be found in B-form helices and other RNA structures and is known to influence ion binding and catalytic function in addition to secondary structure propensity. Accordingly, we have developed a coarse-grained RNA force field to include transitions between the two sugar pucker states in order to accurately reproduce RNA structures and thermodynamics. To model the sugar pucker, we train a coarse-grained collective variable that distinguishes between the two states. Using this collective variable, we interpolate between two sets of force field parameters to properly reflect the structural differences between the two conformational states. The parameters of the entire model are optimized against RNA structures utilizing our contrastive divergence algorithm. Our coarse-grained RNA model opens up the opportunities to study complex RNA dynamics especially those coupled to sugar pucker transitions.

Blockchain-based verifiable and dynamic multi-keyword ranked searchable encryption scheme in cloud computing

Rational miners in the blockchain may admit the validity of search results directly to conserve calculation overhead without executing the validation. Such phenomenon is known as the Verifier's Dilemma that the search results of the blockchain-based searchable encryption scheme would be claimed to have been verified but devoid of valid verification. Besides, the top-k query technique utilized by most existing searchable encryption schemes fails to filter the search results from the user demands during retrieval, which results in massive ineffective access lists with high complexity. Aiming at the two problems, we present a blockchain-based multi-keyword ranked searchable encryption scheme and design a fair payment protocol for multi-user scenarios. Our scheme may achieve public verifiability and user fairness by leveraging the TrueBit network, while the data owner (DO) can withdraw search privileges from the authorized data user (DU). Also, we extend the searchable encryption scheme based on inverted index to multi-DO/multi-DU scenarios, and the HashMap index is used to diminish the response time and space complexity. Moreover, the proposed scheme supports the update of index keywords and files dynamically. To enhance retrieval accuracy, we modify the information divergence algorithm in machine learning and utilize the monotonically weighted aggregation function, which improves retrieval accuracy to around 97%. Finally, Security analysis illustrates correctness and resilience against typical attacks to verify the robustness and utility of the proposed scheme.

A New Deep Learning Restricted Boltzmann Machine for Energy Consumption Forecasting

A key issue in the desired operation and development of power networks is the knowledge of load growth and electricity demand in the coming years. Mid-term load forecasting (MTLF) has an important rule in planning and optimal use of power systems. However, MTLF is a complicated problem, and a lot of uncertain factors and variables disturb the load consumption pattern. This paper presents a practical approach for MTLF. A new deep learning restricted Boltzmann machine (RBM) is proposed for modelling and forecasting energy consumption. The contrastive divergence algorithm is presented for tuning the parameters. All parameters of RBMs, the number of input variables, the type of inputs, and also the layer and neuron numbers are optimized. A statistical approach is suggested to determine the effective input variables. In addition to the climate variables, such as temperature and humidity, the effects of other variables such as economic factors are also investigated. Finally, using simulated and real-world data examples, it is shown that for one year ahead, the mean absolute percentage error (MAPE) for the load peak is less than 5%. Moreover, for the 24-h pattern forecasting, the mean of MAPE for all days is less than 5%.

Neighborhood-based inference and restricted Boltzmann machine for microbe and drug associations prediction.

BackgroundEfficient identification of microbe-drug associations is critical for drug development and solving problem of antimicrobial resistance. Traditional wet-lab method requires a lot of money and labor in identifying potential microbe-drug associations. With development of machine learning and publication of large amounts of biological data, computational methods become feasible.MethodsIn this article, we proposed a computational model of neighborhood-based inference (NI) and restricted Boltzmann machine (RBM) to predict potential microbe-drug association (NIRBMMDA) by using integrated microbe similarity, integrated drug similarity and known microbe-drug associations. First, NI was used to obtain a score matrix of potential microbe-drug associations by using different thresholds to find similar neighbors for drug or microbe. Second, RBM was employed to obtain another score matrix of potential microbe-drug associations based on contrastive divergence algorithm and sigmoid function. Because generalization ability of individual method is poor, we used an ensemble learning to integrate two score matrices for predicting potential microbe-drug associations more accurately. In particular, NI can fully utilize similar (neighbor) information of drug or microbe and RBM can learn potential probability distribution hid in known microbe-drug associations. Moreover, ensemble learning was used to integrate individual predictor for obtaining a stronger predictor.ResultsIn global leave-one-out cross validation (LOOCV), NIRBMMDA gained the area under the receiver operating characteristics curve (AUC) of 0.8666, 0.9413 and 0.9557 for datasets of DrugVirus, MDAD and aBiofilm, respectively. In local LOOCV, AUCs of 0.8512, 0.9204 and 0.9414 were obtained for NIRBMMDA based on datasets of DrugVirus, MDAD and aBiofilm, respectively. For five-fold cross validation, NIRBMMDA acquired AUC and standard deviation of 0.8569 ± −0.0027, 0.9248 ± −0.0014 and 0.9369 ± −0.0020 on the basis of datasets of DrugVirus, MDAD and aBiofilm, respectively. Moreover, case study for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) showed that 13 out of the top 20 predicted drugs were verified by searching literature. The other two case studies indicated that 17 and 17 out of the top 20 predicted microbes for the drug of ciprofloxacin and minocycline were confirmed by identifying published literature, respectively.

The use of accelerometers for the remote detection of mounting in rams and testosterone-treated wethers

It has been estimated that up to a third of all rams have little to no sexual interest in ewes. Despite the prevalence of this issue, it is challenging to monitor the reproductive behaviour of individual sheep in an extensive farming environment. In this study, we developed a single-feature algorithm to detect in-paddock mounting activity from the accelerometer records of rams and androgenised wethers. Tri-axial accelerometers were first deployed on the necks and withers of the rams (n = 15) in a controlled pen test to determine the optimal attachment point for detecting mounting events. A Moving Average Convergence Divergence (MACD) algorithm was applied to accelerometer data with a threshold of 0.3 g. Validation and performance evaluation of the algorithm was based on observed video footage. The MACD was more sensitive and precise when applied to data collected from the withers than the neck (100% vs 89%; 98% vs 86%; respectively). Following the pen test, the MACD was applied to data collected in-paddock from accelerometers attached to the withers of rams (n = 6) and androgenised wethers (n = 8). A MACD + was simultaneously evaluated, which included additional conditions that must be satisfied for the detected peak to be deemed a mounting event. For both algorithms, a series of thresholds were tested. The threshold that returned the highest F1 score (the harmonic mean of precision and sensitivity) for the respective algorithm and male type was selected as the optimal threshold. At their respective optimal thresholds, the MACD + was marginally more precise than the MACD in-paddock for both wethers (91% vs 84%, respectively) and rams (94% vs 84%, respectively). The sensitivity of the MACD in detecting in-paddock mounting behaviour was 91% in rams and 86% in wethers. The MACD + was similarly sensitive at 91% for both rams and wethers. This research demonstrates the success of this algorithm, particularly the MACD+, in detecting mounting activity. Following integration into a commercial sensor and further validation, this algorithm would allow producers to identify rams with low libido and improve reproduction and productivity.

Eclipse Attack Detection for Blockchain Network Layer Based on Deep Feature Extraction

An eclipse attack is a common method used to attack the blockchain network layer; however, detecting eclipse attacks is challenging, and the performance of existing methods is inadequate due to uneven sample distribution, incomplete definition of discriminating features, and weak feature perception. Thus, this paper proposes an eclipse attack traffic detection method based in a custom combination of features and deep learning. To describe the behavior characteristics of attack traffic more accurately, traffic attribute features in there levels are defined in combination with the eclipse attack method. Here, the downstream traffic behavior feature of the eclipse attack is described from the conventional traffic feature, and the frequency distribution characteristics of eclipse attack traffic is by introducing the φ-entropy divergence algorithm. In addition, the structural characteristics of eclipse attack traffic are mapped from the rate of changes in traffic communication and load features. Then, the improved synthetic minority oversampling technique (ISMOTE) up-sampling algorithm is employed to eliminate interference caused by the uneven distribution of eclipse attack traffic samples on the detection results. In addition, the ISMOTE algorithm adjusts the sampling weight of minority class samples, supports automatic clustering and efficient up-sampling of samples, and improves the detection accuracy performance of eclipse attack samples by calculating the local cluster density. Then, deep feature mining is performed on the eclipse attack traffic from the distribution characteristics of space and time series using a CNN and Bi-LSTM. Simultaneously, mining features are fully integrated into mixed feature using the multihead attention mechanism such that the relevance and complementarity of the two feature distributions can be utilized to enhance the model’s ability to perceive the spatiotemporal relationship of the eclipse attack traffic. Finally, the generated multihead attention items are detected for binary classification, and the results are output. Experimental results demonstrate that the proposed method can comprehensively enhance detection performance and sufficiently detect and classify eclipse attack traffic in the blockchain network layer.

Data Cleansing for Salt Dome Dataset With Noise Robust Network on Segmentation Task

Noisy labels seriously degrade the performance of the deep learning models. Especially on segmentation tasks, labels are represented at pixel level, and therefore, it is easier to generate them as noisy labels. In this letter, we aim to cleanse the dataset which contains noisy labels using Kullback–Leibler (KL) divergence algorithm and noise robust loss function. Here, we regard the whole dataset as noisy labels and separate noisy labels into two different parts. One is the strong noisy labels where there are the most noisy labels, which is referred to as incorrect labels, and the other is The weak noisy labels where pixels are incorrect in some parts of the image. The KL algorithm is more efficient in removing the labels which contain the most noise. At the same time, we use noise robust model to remove the labels where pixels are inaccurate only in small parts of the image. Noise robust loss function is robust to noisy labels, and thus, we consider noisy labels when intersection over union (IoU) is lower than a constant threshold despite using noise robust loss function. The effectiveness of our proposed method is assessed using Kaggle’s TGS Salt Identification Challenge dataset. We have demonstrated that using our method, segmentation performance is increased without heavy noisy labels.

Frequency Regulation System: A Deep Learning Identification, Type-3 Fuzzy Control and LMI Stability Analysis

In this paper, the problem of frequency regulation in the multi-area power systems with demand response, energy storage system (ESS) and renewable energy generators is studied. Dissimilarly to most studies in this field, the dynamics of all units in all areas are considered to be unknown. Furthermore time-varying solar radiation, wind speed dynamics, multiple load changes, demand response (DR), and ESS are considered. A novel dynamic fractional-order model based on restricted Boltzmann machine (RBM) and deep learning contrastive divergence (CD) algorithm is presented for online identification. The controller is designed by the dynamic estimated model, error feedback controller and interval type-3 fuzzy logic compensator (IT3-FLC). The gains of error feedback controller and tuning rules of the estimated dynamic model are extracted through the fractional-order stability analysis by the linear matrix inequality (LMI) approach. The superiority of a schemed controller in contrast to the type-1 and type-2 FLCs is demonstrated in various conditions, such as time-varying wind speed, solar radiation, multiple load changes, and perturbed dynamics.

Entropy Estimation Using a Linguistic Zipf-Mandelbrot-Li Model for Natural Sequences.

Entropy estimation faces numerous challenges when applied to various real-world problems. Our interest is in divergence and entropy estimation algorithms which are capable of rapid estimation for natural sequence data such as human and synthetic languages. This typically requires a large amount of data; however, we propose a new approach which is based on a new rank-based analytic Zipf–Mandelbrot–Li probabilistic model. Unlike previous approaches, which do not consider the nature of the probability distribution in relation to language; here, we introduce a novel analytic Zipfian model which includes linguistic constraints. This provides more accurate distributions for natural sequences such as natural or synthetic emergent languages. Results are given which indicates the performance of the proposed ZML model. We derive an entropy estimation method which incorporates the linguistic constraint-based Zipf–Mandelbrot–Li into a new non-equiprobable coincidence counting algorithm which is shown to be effective for tasks such as entropy rate estimation with limited data.

Detecting degraded, prone and transition ecosystems by environmental thresholds and spectral functions

For determining of the desert ecosystem based on transition zones, a quantitative approach was applied in Khorasan Razavi province in northeast of Iran. The spectral and morphological algorithms were implemented in remote-sensing images of MODIS surface reflectance in order to determine the ecogeomorphic thresholds between the transition zones of the semi-arid ecosystems. Furthermore, the spectral angle mapper analysis was applied for the surface conditions and the mathematical morphology algorithm of dilation was used for identifying the recovery and erodibility potential trends in the heterogeneous land surface covers. A detailed assessment of the mapping was achieved by implementation of an iterative self-organized clustering technique (ISODATA) and calculation of separability of formed typologies classes using the transformed divergence algorithm. The assessment of NDVI (normalized difference vegetation index) in each cluster indicates an increasing trend of standard deviation, which shows maximum values near desert thresholds. According to the results, several desert thresholds were detected in susceptible ecosystems to desertification in Khorasan Razavi that were affected by natural and anthropogenic factors. Further evaluation shows the location of the transition zones and the thresholds under changing climatic conditions. In synopsis, in prone areas with the high potential to desertification, the ecosystem is susceptiblt to shift to desert state.

UBMTR: Unsupervised Boltzmann machine-based time-aware recommendation system

Visual media, in today’s world, has swept across most forms of day to day communication. In the paradigm of generative modelling, restricted Boltzmann machines (RBMs) are used to solve complex tasks such as feature extraction, neuroimaging, collaborative filtering, radar target cognition, etc. In this paper, we implement an unsupervised Boltzmann machine-based time-aware recommendation system (UBMTR) which detects underlying hidden features in user-movie ratings data in connection with the time at which each rating was made (temporal information). The model takes ratings and time as a dual-input and outputs binary values via the contrastive divergence algorithm which samples from a Monte Carlo Markov Chain. Arguably, there exists a correlation between the content requested and the temporal conditions, which is exactly what our model tries to exploit. There is seldom any work in the field of recommender systems built using Boltzmann machines that incorporate temporal information, which necessitates research in this domain. RBMs are adept at pattern completion to tackle missing values, and can deal with imbalanced datasets and unstructured data by encoding raw data into latent variables. Using RBM, the UBMTR outperforms many earlier made attempts made at recommendation systems done through CF and deep learning or their hybridized models.