Mohammad Heydari's repositories
Stock-Market-Prediction
in this repository we intend to predict Google and Apple Stock Prices Using Long Short-Term Memory (LSTM) Model in Python. Long Short-Term Memory (LSTM) is one type of recurrent neural network which is used to learn order dependence in sequence prediction problems. Due to its capability of storing past information, LSTM is very useful in predicting stock prices.
Deep-Learning-and-Neural-Networks-Course
This repository contains materials and course projects during attending the Intelligent Systems Course, for more detailed information please have a look at my Final_Report files which have been separately uploaded for each of the projects and consist of all required information about the implementations, analyses, and anything else you may concern about that!
DQN-vs-DDQN-LunarLander-Environment
In this Repository, we intend to implement the DQN and also the DDQN algorithm in case of training an agent to solve the Lunar-Lander problem. there are lots of exciting results after training which have been attached.
Intelligent-Systems-Course
This repository contains materials and course projects during attending the Intelligent Systems Course, for more detailed information please have a look at my Final_Report files which have been separately uploaded for each of the projects and consist of all required information about the implementations, analyses, and anything else you may concern about that!
Text-Generation-Using-Harry-Potter-Book
In this repository, we intend to implement a Recurrent Neural Network that used to generate text using our train data which is the “HARRY POTTER AND THE GOBLET OF FIRE “
Contextual-Embedding-Using-RNNs
Contextual embeddings assign each word a representation based on its context, thereby capturing uses of words across varied contexts and encoding knowledge that transfers across languages. in this repository we tend to implement this concept using Recurrent Neural Networks.
Convex-Optimization-Course
This repository contains materials and course projects during attending the Convex Optimization Course.
Implementing-VGG-19-Using-ImageNet
in this repository we get familiar with the Transfer Learning idea on the ImageNet dataset, in addition, we see how we can employ this vision to implement VGG-19 which is one of the common models of CNNs.
Mohammad-Heydariii
Config files for my GitHub profile.
Segmentation-Using-DeepLab
Deep learning based semantic segmentation Using the Deeplab.
Segmentation-Using-FCN
Deep learning based semantic segmentation Using the FCN.
SGAN
The semi-supervised GAN, or SGAN, model is an extension of the GAN architecture that involves the simultaneous training of a supervised discriminator, unsupervised discriminator, and a generator model. The result is both a supervised classification model that generalizes well to unseen examples and a generator model that outputs plausible examples of images from the domain. in this repository we tend to implement a simplified formation of that.