It is an attempt to bring along various techniques in machine learning and deep learning
- Making Pipelines using sklearn.pipeline
- Using K-fold CrossValidation on Data
- Analysing Algorithm based On learning_curve
- Model Accuracy using validation_curve
- Hyper Parameter Tuning via GridSearchCV
- Plotting and Using Confusion Matrix
- Plotting ROC Curve of Classification
- Implementing simple Majority Vote Classifier
- Using GridSearchCV for HyperParameter selection
- Making A Bagging Classifier
- Using AdaBoost Classifier
- Exploratory data Aanlysis
- Linear Regression from Scratch
- RANSAC Regressor
- LASSO,RIDGE AND ElasticNet
- Polynomial Regression
- Decision Tree Regressor
- Random Forest Regressor
- KMeans Clustering
- Elbow Method Of Clustering
- Quantifying the quality of clustering via silhouette plots
- Organizing clusters as a hierarchical tree
- Agglomerative Clustering
- DBSCAN
- Implementing a perceptron learning algorithm in Python
- Adaptive linear neurons and the convergence of learning
- Adaptive linear neurons with SGD and the convergence of learning
- Basic Operation in Tensorflow
- Spliting tensors in tensorflow
- Creating Tensorflow Data Set from existing Datasets
- Using Dataset from available tensorflow Library
- Using celeb Dataset
- Building Linear Regression Model in Tensorflow
- Model Training Via .compile() and .fit()
- Building Multi Layer Preception for Iris Dataset
- logistic Activation Function
- Class Probability via Softmax Function
- Using Hyperbolic tanh function
- Checking for GPU
- Loading Dataset
- Loading pretrained VGG 16 network
- Training the changed network results
- Checking Test Accuracy and making prediction
- Loading Data Set
- Visualizing Data Set
- Defining Convolutional AutoEncoder
- Training Neural Network
- Checking Network Results
- Loading Data Set
- Visualizing Data Set
- Defining Convolutional Denoiser
- Training Neural Network with Random Noise
- Checking Network Results
- Load VGG 19 (Features)
- Load Content and Style Image
- Content and Style Features
- Gram Matrix
- Updating Target and Calculating Loss
- Final Results
- Creating Data For Prediction
- Definig RNN
- Checking Input and Output Dimension
- Training the RNN
- Single RNN from Scratch
- RNN Cell in Pytorch
- Using RNN on MNSIT Data
- Image RNN in Pytorch