Deep Learning Quick Reference

Dive deeper into neural networks and get your models trained, optimized with this quick reference guide About This Book * A quick reference to all the important deep learning concepts and their implementations * Essential tips, tricks and hacks to training a variety of deep learning models such as CNNs, RNNs, LSTM's and more * Supplemented with essential mathematics and theory, with best practices and safe choices in all the chapters for training and fine-tuning your models in Keras and Tensorflow. Who This Book Is For If you are a Data Scientist or a Machine Learning expert, then this book is a very useful read in training your advanced machine learning and deep learning models. You can also refer this book if you are stuck in-between the neural network modeling and need immediate assistance in getting accomplishing the task smoothly. Some prior knowledge of Python and tight hold on the basics of machine learning is required. What You Will Learn * Solve regression and classification challenges with TensorFlow and Keras * Learn to use Tensor Board for monitoring neural networks and its training * Optimization of Hyperparameter and considerations on safe choices and best practices * Building CNN for image classification from scratch * Use an LSTM on a multivariate input tensor to predict a stock price * How to train seq2seq models to translate text from English to French * Explore Deep Q Network and address autonomous agent challenges * Use two adversarial networks to generate artificial images that appear real In Detail This book will make deep learning techniques more accessible, practical, and consumable to practising Data Scientists. It will move deep learning from academic to application, teaching the reader to apply deep learning through real-world examples.For implementation purposes, we look at the popular Python-based deep learning frameworks such as Keras and Tensorflow, and some quick tricks on how to use them efficiently for deep learning. The book starts with a quick refresh run of deep learning concepts and prepares the readers for the remainder of the book. The reader will then be able to use deep learning for models more commonly solved by linear regression.The book then gradually progresses showing the readers how to use Tensor Board to monitor the training of their deep neural networks and solve binary classification problems using deep learning and learn to optimize hyperparameters in their deep learning models. The book then takes the readers through the practical implementation of training CNN's, RNN's, LSTM's with word embeddings and seq2seq models from scratch. In the final part, the book dives deep into advanced topics like using Deep Q Network to solve an autonomous agent problem and how to use two adversarial networks to generate artificial images that appear real. By the end of this book, the readers will be able to solve real world problems quickly with deep neural networks.