NVIDIA's Full-Color Guide to Deep Learning: All StudentsNeed to Get Started and Get Results
Learning Deep Learning is a complete guide to DL.Illuminating both the core concepts and the
hands-on programming techniquesneeded to succeed this book suits seasoned developers data
scientists analysts but also those with no prior machine learning or statisticsexperience.
After introducing the essential building blocks of deep neural networks such as artificial
neurons and fully connected convolutional and recurrent layers Magnus Ekman shows how to use
them to build advanced architectures includingthe Transformer. He describes how these concepts
are used to build modernnetworks for computer vision and natural language processing (NLP)
includingMask R-CNN GPT and BERT. And he explains how a natural language translatorand a
system generating natural language descriptions of images. Throughout Ekman provides concise
well-annotated code examples usingTensorFlow with Keras. Corresponding PyTorch examples are
provided online andthe book thereby covers the two dominating Python libraries for DL used
inindustry and academia. He concludes with an introduction to neural architecturesearch (NAS)
exploring important ethical issues and providing resources forfurther learning. Exploreand
master core concepts: perceptrons gradient-based learning sigmoidneurons and back
propagation See how DL frameworks make it easier to developmore complicated and useful neural
networks Discover how convolutional neuralnetworks (CNNs) revolutionize image classification
and analysis Apply recurrentneural networks (RNNs) and long short-term memory (LSTM) to text
and othervariable-length sequences Master NLP with sequence-to-sequence networks and
theTransformer architecture Build applications for natural language translation andimage
captioning
