I want to present my heartful gratitude to Aurelien Geron for this book. I'm so glad that I read this book and learned a lot from this book. I will always be thankful to Aurelien Geron to teach me when I was taking steps toward my dream. Thank you so much Aurelien Geron.
This repository contains the code to build various machine learning models from popular book O'Reilly Hands-On Machine Learning with Scikit-Learn & TensorFlow by author Aurelien Geron.
The code is simplified to understand it better with precise & simple explanations that run along with the code. Many models trained in this book use Randomized Search or Grid Search to finetune the set of hyperparameters.
Topics covered so far:
Chapter - 2 (End-to-End Machine Learning Project) Housing Prediction Model
Chapter - 3 (Classification) MNIST Handwritten Numeric Digit Classification Model
Chapter - 4 (Training Models) Linear Regression, Polynomial Regression, Ridge Regression, Lassi Regression, Logistic Regression, Softmax Regression
Chapter - 5 (Support Vecor Machines) Polynomial Kernel, Gaussian RBF Kernel, SVM Classifier on MNIST dataset and SVM Regressor on California Housing Dataset
Chapter - 6 (Decision Trees) DecisionTreeClassifier and DecisionTreeRegressor
Chapter - 7 (Ensemble Learning and Random Forests) Voting Classifiers, Bagging and Pasting, and AdaGrad and Gradient Boosting
Chapter - 8 (Dimensionality Reduction) Principal Component Analysis (PCA)
Chapter - 9 (Up and Running with TensorFlow) Linear Regression, Logistic Regression, Saving and Restoring Models, TensorBoard
Chapter - 10 (Introduction to Artificial Neural Networks) Deep Neural Networks
Chapter - 11 (Training Deep Neural Nets) MNIST Classification with >99% accuracy, Batch Normalization, Gradient Clipping, Reusing Pretrained Layers, Learning Rate Scheduling, Regularization, Dropout and Transfer Learning
Chapter - 13 (Convolutional Neural Networks) Pooling Layer, CNN on MNIST and Classifying Large Images using Inception
Chapter - 14 (Recurrent Neural Networks) Training RNNs, Deep RNNs, Applying Dropout, Long Short Term Memory (LSTM) cell and Embeddings