Skip to content

using scikit learn tool to perform regression, classification and tensorflow/keras/pytorch to implement artificial neural network(ANN), convolutional neural network(CNN), recurrent neural networks (RNN), Self Organizing Maps, Boltzmann Machines, AutoEncoders

Notifications You must be signed in to change notification settings

chakrond/Machine-Learning-Python

Repository files navigation

==============================================
Machine Learning
==============================================

This repo contains the example work of the following:

  • Supervised Learning
    • Regression
      • Simple Linear Regression

      • Multiple Linear Regression

      • Polynomial Regression

      • Support Vector Regression (SVR)

      • Decision Tree Regression

      • Random Forest Regression

      • Regression Comparison
        Regression

-----------------------------------------------------------------------------------------------------

  • Classification
    • Logistic Regression

    • K-Nearest Neighbors (K-NN)

    • Support Vector Machine (SVM)

    • Kernel SVM

    • Naive Bayes

    • Decision Tree Classification

    • Random Forest Classification

      Classification Comparison
      Classification

      Classification Decision Boundary Comparison
      Classification_Decission_Boundary

-----------------------------------------------------------------------------------------------------

  • Unsupervised Learning

    • Clustering
      • K-Means Clustering
      • Hierarchical Clustering

    Clustering Comparison
    Clustering Comparison

    Optimal Comparison
    Optimal Comparison

-----------------------------------------------------------------------------------------------------

  • Association Rule Learning
    • Apriori
    • Eclat

-----------------------------------------------------------------------------------------------------

  • Reinforcement Learning
    • Upper Confidence Bound (UCB)
    • Thompson Sampling

-----------------------------------------------------------------------------------------------------

UCB vs Thompson at iteration of 500
UCB_vs_Thompson_500

UCB vs Thompson at iteration of 10000
UCB_vs_Thompson_1000

-----------------------------------------------------------------------------------------------------

  • Natural Language Processing

    • Bag of words (CountVectorizer, Regression)
  • CountVectorizer & Prediction(Regression)
    NLP_BagOfWords

-----------------------------------------------------------------------------------------------------
Dimensionality Reduction

  • Supervised

    • Linear Discriminant Analysis (LDA)
  • Unsupervised

    • Principal Component Analysis (PCA)
    • Kernel PCA

Decision Boundary Comparison (Training Set)
decision_boundary_compare

Confusion Matrix Comparison & Accuracy Score (Test Set)
confusion_mat_compare

-----------------------------------------------------------------------------------------------------

  • XGBoost
    • XGBoost Classifier

-----------------------------------------------------------------------------------------------------

  • Model Validation
    • k-Fold Cross Validation
    • Grid Search

============================================================================================
Deep Learning
============================================================================================

  • Supervised

    • Artificial Neural Networks (ANN)

      • Binary Classification
        Figure_1

      • Model Performance Scores
        perf_scores

      • Multiple Classification - Experiments over learning rate parameters
        multiple_classification_softmax

      • Overall Classification Performance (Softmax) - Experiments over learning rate parameters
        classification_performance

      • Experiments over hidden layers parameters
        Exprms_hLayers

      • Experiments over number of units per hidden layer parameters
        hLayers_nUnits

      • Overall Classification Accuracy
        overall_performance_category

      • Data Inspection
        data inspection

      • Result Correlation
        results_correlation

    • Fully-connected Feedforward Neural Network (FFN)

      • MNIST Image Data
        MNIST_image

      • Data Inspection
        data_inspection

      • How data looks like
        download

      • Model's Weights Distribution
        weights_distribution

      • Model's Performance Scores
        perf_scores_mnist

    • Convolutional Neural Networks (CNN)

      • Feature maps
        1st Convolution layer
        feature map_1v2 2nd Convolution layer
        feature map_2v2

      • Feature maps[occlusion sample]
        Original
        CNN_occlusion 1st Convolution layer
        feature map_occl_1 2nd Convolution layer
        feature map_occl_2

      • Denoise
        denoise

      • Parameters Predictions
        params_prediction params_prediction_values

      • EMNIST

        • EMNIST Predictions
          EMNIST_prediction EMNIST_prediction_stats EMNIST_prediction_errors
      • CIFAR10

        • EMNIST Predictions
          CIFAR10_prediction CIFAR10_ftMap_0v0 CIFAR10_prediction_accByGroupv0
    • Recurrent Neural Networks (RNN)

    • Generative Adversarial Network (GAN)

      • Generated Image
        • FMNIST
          generated_res_fmnist
        • MNIST
          generated_res_mnist

-----------------------------------------------------------------------------------------------------

  • Unsupervised

    • Self Organizing Maps
    • Boltzmann Machines
    • AutoEncoders
      • Denoised
        AE_Denoised

      • Occlusion
        AE_Denoised_Occlusion

      • Occlusion Effect
        Effect of occlusion

      • Latent Activation
        hist

      • Latent Values Histogram
        LatentValues

      • Latent Values PCA
        PCA

-----------------------------------------------------------------------------------------------------

  • Math Function

    • Sigmoid
      sigmoid_relu

    • Softmax
      softmax

    • Mean Sample
      hist_sampling

    • Gradient Descent 1D Animated
      gradient_descent1D_animated

    • Gradient Descent 2D Animated

      gradient_descent_2D

About

using scikit learn tool to perform regression, classification and tensorflow/keras/pytorch to implement artificial neural network(ANN), convolutional neural network(CNN), recurrent neural networks (RNN), Self Organizing Maps, Boltzmann Machines, AutoEncoders

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published