https://github.com/chhayac/machine-learning-notebooks
15+ Machine/Deep Learning Projects in Ipython Notebooks
https://github.com/chhayac/machine-learning-notebooks
cifar-10 ipython-notebook iris iris-dataset keras keras-neural-networks keras-tensorflow linear-regression machine-learning multivariate-regression notebook tensorflow tensorflow-models
Last synced: 6 months ago
JSON representation
15+ Machine/Deep Learning Projects in Ipython Notebooks
- Host: GitHub
- URL: https://github.com/chhayac/machine-learning-notebooks
- Owner: chhayac
- Created: 2017-12-16T06:18:15.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2020-04-03T05:31:41.000Z (about 5 years ago)
- Last Synced: 2024-10-10T08:43:55.934Z (7 months ago)
- Topics: cifar-10, ipython-notebook, iris, iris-dataset, keras, keras-neural-networks, keras-tensorflow, linear-regression, machine-learning, multivariate-regression, notebook, tensorflow, tensorflow-models
- Language: Jupyter Notebook
- Homepage:
- Size: 3.84 MB
- Stars: 106
- Watchers: 3
- Forks: 99
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Machine Learning and Deep learning Notebooks
| Notebook Description| Link | Notes |
| -------------------| -----|--------|
| Iris Flower Classification | [Iris_flower_classification.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Iris_flower_classification.ipynb) | Build a neural network model using Keras & Tensorflow. Evaluated the model using scikit learn's k-fold cross validation. |
| Recognizing CIFAR-10 images (Part I - Simple model) | [Recognizing-CIFAR-10-images-Simple-Model.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Recognizing-CIFAR-10-images-Simple-Model.ipynb) | Build a simple Convolutional Neural Network(CNN) model to classify CIFAR-10 image dataset with Keras deep learning library achieving classification accuracy of 67.1%. |
| Recognizing CIFAR-10 images (Part II - Improved model) | [Recognizing-CIFAR-10-images-Simple-Model.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Recognizing-CIFAR-10-images-Improved-Model.ipynb) | Build an improved CNN model by adding more layers with Keras deep learning library achieving classification accuracy of 78.65%. |
| Recognizing CIFAR-10 images (Part III - Data Augmentation) | [Recognizing-CIFAR-10-images-Improved-Model-Data-Augmentation.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Recognizing-CIFAR-10-images-Improved-Model-Data-Augmentation.ipynb) | Build an improved CNN model by data augmentation with Keras deep learning library achieving classification accuracy of 80.73%. |
| Traffic Sign Recognition using Deep Learning | [Traffic-Sign-Recognition.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Traffic-Sign-Recognition.ipynb) | Build a deep learning model to detect traffic signs using the German Traffic Sign Recognition Benchmark(GTSRB) dataset achieving an accuracy of 98.4%. |
| Movie Recommendation Engine | [Movie_Recommendation_Engine.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Movie_Recommendation_Engine.ipynb) | Build a movie recommendation engine using k-nearest neighbour algorithm implemented from scratch. |
| Linear Regression | [Linear_Regression.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Linear_Regression.ipynb) | Build a simple linear regression model to predict profit of food truck based on population and profit of different cities. |
| Multivariate Linear Regression | [Multivariate_Linear_Regression.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Multivariate_Linear_Regression.ipynb) | Build a simple multivariate linear regression model to predict the price of a house based on the size of the house in square feet and number of bedrooms in the house. |
| Sentiment Analysis of Movie Reviews| [Sentiment_Analysis.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Sentiment_Analysis.ipynb)| Experiment to analyze sentiment according to their movie reviews. |
| Wine quality prediction | [Predicting_wine_quality.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Predicting_wine_quality.ipynb)| Experiment to predict wine quality with feature selection (In progress). |
| Unsupervised Learning | [unsupervised_learning-Part_1.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/unsupervised_learning-Part_1.ipynb)| Hands-on with Unsupervised learning. |
| Autoencoders using Fashion MNIST| [Autoencoder_Fashion_MNIST.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Autoencoder_Fashion_MNIST.ipynb)| Building an autoencoder as a classifier using Fashion MNIST dataset. |
| Logistic Regression| [Logistic_Regression.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/Logistic_Regression.ipynb)| Build a logistic regression model from scratch - Redoing it |
| Fuzzy string matching| [fuzzywuzzy.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/fuzzy_string_matching.ipynb)| To study how to compare strings and determine how similar they are in Python. |
| Spam email classification| [spam_email_classification.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/spam_email_classification.ipynb)| Build a spam detection classification model using an email dataset.
| Customer churn prediction| [customer_churn_prediction.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/customer_churn_prediction.ipynb)| To predict if customers churn i.e. unsubscribed or cancelled their service.- In Progress|
| Predicting Credit Card Approvals| [predicting_credit_card_approvals.ipynb](https://github.com/chhayac/Machine-Learning-Notebooks/blob/master/predicting_credit_card_approvals.ipynb)| To predict the approval or rejection of a credit card application|