rabia174/Machine-Learning-From-Scratch-PDFs rabia174/Machine-Learning-From-Scratch-PDFs

  • Stars
    star
    1
  • Language
    Jupyter Notebook
  • Created over 4 years ago
  • Updated over 4 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
rabia174/Machine-Learning-From-Scratch-PDFs
github

rabia174

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Start from crash course of Python, continue with the Numpy, Matplotlib and Machine Learning with exercises. This pdfs are referenced and cited from the University of Helsinki, Finland Machine Learning Summer Course.

More Repositories

1

COVID-19-Deep-Learning-CNN-Model

Here, I created my own deep learning(CNN) model for early detection of COVID-19 from chest x-ray images. If we were to answer the question that why we need a deep learning model for early detection of COVID-19 from chest x-ray images, we can say the followings, doctors have seen that even if the test kits desined for diagnosis results in negative, the real results are positive for some patients when they review the chest X-ray images. For now the public dataset contains less amount of data which you can see in the dataset2 folder. We get this dataset from open-source https://github.com/ieee8023/covid-chestxray-dataset, but for sure it is not enough to train a proper deep learning model. But just to show that how easy it is to create an AI for the early detection of these kind of viruses. Just keep in mind that this cannot be used for diagnosis without training many more images in high-resolution and professinal medical tests. There you go! Let's work together to fight against COVID-19. As a tool, I used Keras with Tensorflow background, and the model can be improved by addig more convolution and pooling layers, and increasing the number of feature detectors'. Don't forget to upvote. Best Regards.
Jupyter Notebook
29
star
2

Kuopio-University-Hospital-Microsurgery-Department-Visualize-Interactive-Software

The Visualize Interactive is a desktop software developed to visualize physiological signals during the activities called mesh alignment, knotting, and go-around which are done by the participants of the research team who participated in the synchronization and analysis of the biomarkers under noise and stress. You can download and install the application by using the following link, https://drive.google.com/drive/folders/1ZKrVuZ17Yat7EvErFob9E1PCWSaoPHpm
Python
2
star
3

Transfer_Learning_Covid-19_Pneumonia_Healthy

This deep learning model(CNN) uses Transfer learning by Feature Extraction and Fine Tuning in order to make multiclass-classification between COVID-19, Pneumonia and Healthy images.
Jupyter Notebook
1
star
4

COVID-19_In_Italy_Exploratory_Data_Analysis

This repository is created in order to analyze why COVID-19 spreading faster in North Italy when compared to other regions of Italy.
1
star
5

COVID-19_Detection_Desktop_Application_Software

It is a Python desktop application software which takes a chest x-ray image and then produces probabilities belong to each class with a Grad-CAM.
Python
1
star
6

Computer-Graphics-with-WebGL---Sample-Projects

2D and 3D Transformations, Lighting, Texture Properties, and more...
JavaScript
1
star
7

Data-Science-Internship-Works-at-TURKSAT

Aim of this internship is first to learn about data science, big data visualization, machine learning and deep learning, implement the following tools: anaconda, jupyter notebook, spider and the libraries following: numpy,pandas,matplotlib,seaborn,plotly,scikit-learn by describing the platforms used by data scientists like kaggle and finally integrating the machine learning into e-government platform.
Jupyter Notebook
1
star
8

Synchronization-and-Analysis-of-the-Biomarkers-Under-Noise-and-Stress-Project

So, in this paper, we will propose a data summary tables, visualizations which make some comparisons by using different properties of participants, and a deep learning model which first train the model by using the experiment outcomes analysis dataset and then test the accuracy, so that we can understand how much use the collected data is. Visualizations will be provided by using both R and Python and their rich visualization tools libraries. These visualizations consist of comparisons between the participants who are working in a silent environment and noise environment. You may not see clearly some of the visualizations on Github.You can download and run yourself with the provided *.csv file.
Jupyter Notebook
1
star