vipul2001 / Machine-Learninng-and-Deep-Learning

It is an attempt to bring along various techniques in machine learning and deep learning

Machine-Learninng

It is an attempt to bring along various techniques in machine learning and deep learning

1. Model Evaluation And Hyper Parameter Tuning

1. Making Pipelines using sklearn.pipeline
2. Using K-fold CrossValidation on Data
3. Analysing Algorithm based On learning_curve
4. Model Accuracy using validation_curve
5. Hyper Parameter Tuning via GridSearchCV
6. Plotting and Using Confusion Matrix
7. Plotting ROC Curve of Classification

2. Combining Model for Ensemble Learning

1. Implementing simple Majority Vote Classifier
2. Using GridSearchCV for HyperParameter selection
3. Making A Bagging Classifier
4. Using AdaBoost Classifier

3. Regression Analysis

1. Exploratory data Aanlysis
2. Linear Regression from Scratch
3. RANSAC Regressor
4. LASSO,RIDGE AND ElasticNet
5. Polynomial Regression
6. Decision Tree Regressor
7. Random Forest Regressor

4. Clustering Analysis

1. KMeans Clustering
2. Elbow Method Of Clustering
3. Quantifying the quality of clustering via silhouette plots
4. Organizing clusters as a hierarchical tree
5. Agglomerative Clustering
6. DBSCAN

5. Classification Analysis

1. Implementing a perceptron learning algorithm in Python
2. Adaptive linear neurons and the convergence of learning
3. Adaptive linear neurons with SGD and the convergence of learning

6. Basics of Tensorflow

1. Basic Operation in Tensorflow
2. Spliting tensors in tensorflow
3. Creating Tensorflow Data Set from existing Datasets
4. Using Dataset from available tensorflow Library
5. Using celeb Dataset

7. Basic Tensorflow Neural Network

1. Building Linear Regression Model in Tensorflow
2. Model Training Via .compile() and .fit()
3. Building Multi Layer Preception for Iris Dataset
4. logistic Activation Function
5. Class Probability via Softmax Function
6. Using Hyperbolic tanh function

8. Transfer Learning In Pytorch using VGG16

1. Checking for GPU
2. Loading Dataset
3. Loading pretrained VGG 16 network
4. Training the changed network results
5. Checking Test Accuracy and making prediction

9. Convoluional Autoencoders in Pytorch

1. Loading Data Set
2. Visualizing Data Set
3. Defining Convolutional AutoEncoder
4. Training Neural Network
5. Checking Network Results

10.Image noise reduction using auto encoder

1. Loading Data Set
2. Visualizing Data Set
3. Defining Convolutional Denoiser
4. Training Neural Network with Random Noise
5. Checking Network Results

11. Neural Style Transfer

1. Load VGG 19 (Features)
2. Load Content and Style Image
3. Content and Style Features
4. Gram Matrix
5. Updating Target and Calculating Loss
6. Final Results

12. Intro to RNN

1. Creating Data For Prediction
2. Definig RNN
3. Checking Input and Output Dimension
4. Training the RNN

13. RNN in Pytorch

1. Single RNN from Scratch
2. RNN Cell in Pytorch
3. Using RNN on MNSIT Data
4. Image RNN in Pytorch