Generative networks are effective tools for digital materials (DM) inverse design. However, the optimization performance of generative is restricted by increasing discrepancy between optimized input and prescribed domain as design loop increases. Herein, a correction technique incorporated into deep neural network (GDNN) convolutional (GDCNN). The performed pulling machine learning (ML)-optimiz...

Feed-forward deep neural networks have been used extensively in various machine learning applications. Developing a precise understanding of the underling behavior of neural networks is crucial for their efficient deployment. In this paper, we use an information theoretic approach to study the flow of information in a neural network and to determine how entropy of information changes between co...

We present a new method to approximate posterior probabilities of Bayesian Network using Deep Neural Network. Experiment results on several public Bayesian Network datasets shows that Deep Neural Network is capable of learning joint probability distribution of Bayesian Network by learning from a few observation and posterior probability distribution pairs with high accuracy. Compared with tradi...

Phishing is an online crime in which a cybercriminal tries to persuade internet users reveal important and sensitive personal information, such as bank account details, usernames, passwords, social security numbers, the phisher, usually for mean purposes. The target victim of fraud suffers financial loss, well loss information reputation. Therefore, it essential identify effective approach phis...

Deep learning has been extensively used various aspects of computer vision area. Deep learning separate itself from traditional neural network by having a much deeper and complicated network layers in its network structures. Traditionally, deep neural network is abundantly used in computer vision tasks including classification and detection and has achieve remarkable success and set up a new st...

Deep learning is a popular technique in modern online and offline services. Deep neural network based learning systems have made groundbreaking progress in model size, training and inference speed, and expressive power in recent years, but to tailor the model to specific problems and exploit data and problem structures is still an ongoing research topic. We look into two types of deep ‘‘multi-’...

In recent years, neural network language models (NNLMs) have shown success in both peplexity and word error rate (WER) compared to conventional n-gram language models. Most NNLMs are trained with one hidden layer. Deep neural networks (DNNs) with more hidden layers have been shown to capture higher-level discriminative information about input features, and thus produce better networks. Motivate...

Recent developments in the field of deep learning have shown that convolutional networks with several layers can approach human level accuracy in tasks such as handwritten digit classification and object recognition. It is observed that the state-of-the-art performance is obtained from model ensembles, where several models are trained on the same data and their predictions probabilities are ave...

Pretraining is widely used in deep neutral network and one of the most famous pretraining models is Deep Belief Network (DBN). The optimization formulas are different during the pretraining process for different pretraining models. In this paper, we pretrained deep neutral network by different pretraining models and hence investigated the difference between DBN and Stacked Denoising Autoencoder...

Compression of deep neural networks (DNNs) for memoryand computation-efficient compact feature representations becomes a critical problem particularly for deployment of DNNs on resource-limited platforms. In this paper, we investigate lossy compression of DNNs by weight quantization and lossless source coding for memory-efficient inference. Whereas the previous work addressed non-universal scal...