Deep Learning with Theano

Key FeaturesLearn Theano basics and evaluate your mathematical expressions faster and in an efficient mannerLearn the design patterns of deep neural architectures to build efficient and powerful networks on your datasetsApply your knowledge to concrete fields such as image classification, object detection, chatbots, machine translation, reinforcement agents, or generative models.Book DescriptionThis book offers a complete overview of Deep Learning with Theano, a Python-based library that makes optimizing numerical expressions and deep learning models easy on CPU or GPU.The book provides some practical code examples that help the beginner understand how easy it is to build complex neural networks, while more experimented data scientists will appreciate the reach of the book, addressing supervised and unsupervised learning, generative models, reinforcement learning in the fields of image recognition, natural language processing, or game strategy.Further, the book speaks about image recognition tasks that range from simple digit recognition, image classification, object localization, image segmentation, to image captioning. Natural language processing examples include text generation, chatbots, machine translation, and question answering. The last example deals with generating random data that looks real and solving games such as in the Open-AI gym.At the end, this book sums up the best performing nets for each task. While early research results were based on deep stacks of neural layers, in particular, convolutional layers, the book presents the principles that improved the efficiency of these architectures, in order for the reader to build new custom nets.What you will learnGet familiar with Theano and deep learningProvide examples in supervised, unsupervised, generative, or reinforcement learning.Discover the main principles to design efficient deep learning nets: convolutions, residual connections, and recurrent connections.Use Theano on real-world computer vision data sets, such as for digit classification and image classification.Extend the use to natural language processing tasks, for chatbots or machine translationCover artificial intelligence driven strategies for a robot to solve games or learn from an environmentGenerate synthetic data that looks real with generative modelingGet familiar with Lasagne and Keras, two frameworks built on top of TheanoAbout the AuthorDuring more than 10 years, Christopher Bourez has been an evangelist, innovator, entrepreneur, writer, and adviser in artificial intelligence.He graduated in 2005 from the Ecole Polytechnique and Ecole Normale Supérieure in Paris with a master of science in the field of machine learning, computer vision, and mathematics.In 2007, he founded his first company in computer vision with the first “Shazam of the image” mobile app.Since 2015, he is the editor of a blog , testing some of the modern technologies in computer science, covering deep learning, distributed computing, multiplatform technologies, devops, computer science standards and patterns, and is visited by more than 30 000 monthly engineers.Lately, he has been advising corporations and start-up companies as an expert in computer science, machine learning, and, in particular, deep learning.

Author: Christopher Bourez

Learn more