Improving return forecasting is very important for both investors and researchers in financial markets. In this study we try to aim this object by two new methods. First, instead of using traditional variable, gold prices have been used as predictor and compare the results with Goyal's variables. Second, unlike previous researches new machine learning Algorithm called Deep learning (DP) has been used to improve return forecasting and then compare the results with historical average methods as bench mark model and use Diebold and Mariano’ s and West’ s statistic (DMW) for statistical evaluation. Results indicate that the applied DP model has higher accuracy compared to historical average model. It also indicates that out of sample prediction improvement does not always depend on high input variables numbers. On the other hand when using gold price as input variables, it is possible to improve this forecasting capability. Result also indicate that gold price has better accuracy than Goyal's variable to predicting out of sample return.

An optimization Algorithm based on training and learning is formed based on the process of training and learning in a class. A Deep neural network is one of the types of feedforward neural networks whose connection pattern among its neurons is inspired by the visual cortex of animals' brain. The present study considers decreasing prediction error for the types of time series and the uncertainty in estimation parameters, improving the structure of the Deep neural network and increasing response speed in the proposed neural network method; besides, the competitive performance and the collaboration among the neurons of Deep neural network are also increased. Selected data is related to Qeshm weather (suitable weather conditions to study our purpose) prediction during 2016 onwards. In this study, for the purpose of analyzing the prediction issue of power consumption of domestic expenses in the indefinite and severe fluctuation mode, we decided to combine two methods of Long Short-Term Memory and Convolutional Neural Network. For the training of the Deep network, the BP Algorithm is used.

: In this paper, the operation scheduling of Microgrids (MGs), including Distributed Energy Resources (DERs) and Energy Storage Systems (ESSs), is proposed using a Deep Reinforcement Learning (DRL) based approach. Due to the dynamic characteristic of the problem, it firstly is formulated as a Markov Decision Process (MDP). Next, Deep Deterministic Policy Gradient (DDPG) Algorithm is presented to minimize total operational costs by learning the optimal strategy for operation scheduling of MG systems. This model-free Algorithm deploys an actor-critic architecture which can not only model the continuous state and action spaces properly but also overcome the curse of dimensionality. In order to evaluate the efficiency of the proposed Algorithm, the results were compared with the analytical method and a Q-based learning Algorithm which demonstrates the capability of the DDPG method from the aspects of convergence, running time, and total costs.

Now diagnostic methods with the help of machine learning have been able to help doctors in this field. One of the most important of these methods is Deep learning, which has gotten good answers in images containing cancer. Increasing the accuracy of Deep neural network classifiers can increase the diagnosis of breast cancer. In this paper, we have tried to achieve higher accuracy than non-parallel models with the help of a parallel model of a Deep neural network. The proposed method is a parallel hybrid method combining AlexNet and VGGNet networks applied in parallel to mammographic images. The database used in this article is INBreast. The results obtained from this method show a 4% increase compared to some other classification models so that in the type of density 1, it has achieved about 99.7%. In the case of other densities, an accuracy of nearly 99% has been obtained.

Distributed Denial of Service (DDoS) attacks are among the primary concerns in internet security today. Machine learning can be exploited to detect such attacks. In this paper, a multi-layer perceptron model is proposed and implemented using Deep machine learning to distinguish between malicious and normal traffic based on their behavioral patterns. The proposed model is trained and tested using the CICDDoS2019 dataset. To remove irrelevant and redundant data from the dataset and increase learning accuracy, feature selection is used to select and extract the most effective features that allow us to detect these attacks. Moreover, we use the grid search Algorithm to acquire optimum values of the model’s hyperparameters among the parameters’ space. In addition, the sensitivity of accuracy of the model to variations of an input parameter is analyzed. Finally, the effectiveness of the presented model is validated in comparison with some state-of-the-art works.

Recently, a number of Extreme Learning Machine (ELM) based training Algorithms have been introduced for training Deep neural network structures. ELM based Auto-Encoder (ELM-AE) is one such Algorithm that has been used for making multilayer structures and tuning parameters of each layer. In a simple ELM-AE training Algorithm, the weights of the first layer are initialized randomly. This issue is a leading factor in producing reconstruction error. The frequent use of ELM-AE in Deep network layers results in propagating such errors through Deep structures and in decreasing performance as a consequent. In this paper, we introduce a multilayer structure and a new learning Algorithm to train it that prevents error propagation. In order to boost the performance of the model, the parameters in the first layer are initialized by a novel type of ELM-AE called Repeated-AE (RAE) rather than by a random selection method. This RAE-based technique determines the parameters in the first layer far better than do the other ELM-AE existed methods. Next, a single hidden layer ELM is applied for handling the classification task. Experimental results for data classification show that the proposed method outperforms some other methods in terms of the average accuracy over all datasets by amounts of 4%, 26%, 17% and 31%. Eventually, so as to verify the performance of the proposed multilayer ELM-AE in application, we used this model to reconstruct images. The reconstructed images obtained by our approach appeared visually a lot better compared to those obtained by the other methods do.

This study aimed to present an explanatory model of stock price using Deep learning Algorithm for companies listed in the Tehran Stock Exchange. In this study, a Deep learning network was used to predict stock prices. The study was applied-developmental research in terms of purpose. To test the research questions, accounting data were prepared from 2011 to 2020 and input variables were calculated based on it for the model. The method of systematic elimination sampling has been used in this study. The results indicated that the precisions of prediction has a high precisions in the Deep learning model. The proposed Algorithm was reviewed according to its prediction accuracy and modeling cost. According to the data volume, it was found that the prediction accuracy in the Deep learning model has a relative superiority and the diagram of performance characteristic and AUC criteria also showed this superiority in detection power.