An Efficient Normalized Restricted Boltzmann Machine for Solving Multiclass Classification Problems

Aamir, Muhammad; Mohd, Nazri; Wahid, Fazli; Mahdin, Hairulnizam

doi:10.14569/ijacsa.2019.0100856

Cited by 5 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This variation makes it a challenging dataset to be used to test the models. The variation datasets of MNIST are standard (basic), random-noise background digits (bg-rand), and rotation and image background digits (bg-img-rot) [28]. The first MNIST basic (mnist-basic) comprises the standard MNIST image without any changes.…”

Section: Methodsmentioning

confidence: 99%

Auto-Encoder Variants for Solving Handwritten Digits Classification Problem

Aamir¹,

Nawi²,

Mahdin³

et al. 2020

IJFIS

Self Cite

View full text Add to dashboard Cite

Auto-encoders (AEs) have been proposed for solving many problems in the domain of machine learning and deep learning since the last few decades. Due to their satisfactory performance, their multiple variations have also recently appeared. First, we introduce the conventional AE model and its different variant for learning abstract features from data by using a contrastive divergence algorithm. Second, we present the major differences among the following three popular AE variants: sparse AE (SAE), denoising AE (DAE), and contractive AE (CAE). Third, the main contribution of this study is performing the comparative study of the aforementioned three AE variants on the basis of their mathematical modeling and experiments. All the variants of the standard AE are evaluated on the basis of the MNIST benchmark handwritten digit dataset for classification problem. The observed output reveals the benefit of using the AE model and its variants. From the experiments, it is concluded that CAE achieved better classification accuracy than those of SAE and DAE.

show abstract

Section: Methodsmentioning

confidence: 99%

Auto-Encoder Variants for Solving Handwritten Digits Classification Problem

Aamir¹,

Nawi²,

Mahdin³

et al. 2020

IJFIS

Self Cite

View full text Add to dashboard Cite

show abstract

“…The structure diagram of RBM is shown in Figure 8(a). RBM can be broadly extended to its respective variants when considering visible sparse count or real-valued data like, replicated softmax RBM [112], Fuzzy RBM (FRBM) [24], Fuzzy Removing Redundancy RBM (F3RBM) [91], Gaussian-Bernoulli RBM (GBRBM) [140], and Normalized RBM (NRBM) [3]. Deep Belief Networks (DBN) is another probabilistic graphic model that offers a joint probability distribution over the observable labels and data [55].…”

Section: Probabilistic Graphical Modelsmentioning

confidence: 99%

Recent Advances and Trends in Multimodal Deep Learning: A Review

Summaira¹,

Li²,

Shoib³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep Learning has implemented a wide range of applications and has become increasingly popular in recent years. The goal of multimodal deep learning is to create models that can process and link information using various modalities. Despite the extensive development made for unimodal learning, it still cannot cover all the aspects of human learning. Multimodal learning helps to understand and analyze better when various senses are engaged in the processing of information. This paper focuses on multiple types of modalities, i.e., image, video, text, audio, body gestures, facial expressions, and physiological signals. Detailed analysis of past and current baseline approaches and an in-depth study of recent advancements in multimodal deep learning applications has been provided. A fine-grained taxonomy of various multimodal deep learning applications is proposed, elaborating on different applications in more depth. Architectures and datasets used in these applications are also discussed, along with their evaluation metrics. Last, main issues are highlighted separately for each domain along with their possible future research directions.CCS Concepts: • Computing methodologies → Machine learning; • Information systems → Multimedia and multimodal retrieval.

show abstract

“…The major phenomenon of neuroevolution is that the neural network structure, rules, parameters are generated and controlled by an evolutionary algorithm [42]. The next evolutionary intelligence technique is learning classifiers systems (LCS) which is AI approach combining the discovery and learning components [43]. For making various types of predictions, LCS seeks procedures for identification of context dependent rules that use piecewise manner for collecting, storing and applying knowledge.…”

Section: Related Workmentioning

confidence: 99%

An Enhanced Firefly Algorithm Using Pattern Search for Solving Optimization Problems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Firefly Algorithm (FA) is one of the most recently introduced stochastic, nature-inspired, meta-heuristic approaches used for solving optimization problems. The conventional FA use randomization factor during generation of solution search space and fireflies position changing, which results in imbalanced relationship between exploration and exploitation. This imbalanced relationship causes in incapability of FA to find the most optimum values at termination stage. In the proposed model, this issue has been resolved by incorporating PS at the termination stage of standard FA. The optimized values obtained from the FA are set as the initial starting points for the PS algorithm and the values are further optimized by PS to get the most optimal values or at least better values than the values obtained by conventional FA during its maximum number of iterations. The performance of the newly developed FA-PS model has been tested on eight minimization functions and six maximization functions by considering various performance evaluation parameters. The results obtained have been compared with other optimization algorithms namely genetic algorithm (GA), standard FA, artificial bee colony (ABC), ant colony optimization (ACO), differential equations (DE), bat algorithm (BA), grey wolf optimization (GWO), Self-Adaptive Step Firefly Algorithm (SASFA), and FA-Cross algorithm in terms of convergence rate and various numerical performance evaluation parameters. A significant improvement has been observed in the solution quality by embedding PS in the standard FA at the termination stage. The result behind this improvement is the better exploration and exploitation of the solution search space at this stage.

show abstract

An Efficient Normalized Restricted Boltzmann Machine for Solving Multiclass Classification Problems

Cited by 5 publications

References 33 publications

Auto-Encoder Variants for Solving Handwritten Digits Classification Problem

Auto-Encoder Variants for Solving Handwritten Digits Classification Problem

Recent Advances and Trends in Multimodal Deep Learning: A Review

An Enhanced Firefly Algorithm Using Pattern Search for Solving Optimization Problems

Contact Info

Product

Resources

About