Andrew W. Trask

Andrew Trask is the founding member of Digital Reasoning’s machine learning lab, where deep learning approaches to natural language processing, image recognition, and audio transcription are being researched. Within several months, Andrew and his research partner exceeded best published results in sentiment classification and part-of-speech tagging. He trained the world’s largest artificial neural network with over 160 billion parameters, the results of which he presented with his coauthor at The International Conference on Machine Learning. Those results were published in the Journal of Machine Learning. He is currently the product manager of text and audio analytics at Digital Reasoning, responsible for driving the analytics roadmap for the Synthesys cognitive computing platform, for which deep learning is a core competency.

books by Andrew W. Trask

Exploring Deep Learning
  • January 2020
  • ISBN 9781617297816
  • 67 pages
Included with a Manning Online subscription

Exploring Deep Learning combines three chapters from Manning books, selected by author and experienced deep learning practitioner Andrew Trask. In it, you’ll get a high-level view of basic deep learning concepts and take a look at different learning techniques, including supervised vs. unsupervised learning and parametric vs. non-parametric learning. Using Tensorflow, you’ll also explore more advanced concepts, such as classification, recurrent neural networks (RNNs), seq2seq architecture, vector representation, and embedding natural language as you build a working chatbot. With this timely and accessible sampler, you’ll have a firm foundation for building on your deep learning education as you discover for yourself deep learning’s potential for the future.

Grokking Deep Learning
  • January 2019
  • ISBN 9781617293702
  • 336 pages
Included with a Manning Online subscription
  • printed in black & white
  • Available translations: Complex Chinese, German, Japanese, Polish, Russian, Simplified Chinese

Grokking Deep Learning teaches you to build deep learning neural networks from scratch! In his engaging style, seasoned deep learning expert Andrew Trask shows you the science under the hood, so you grok for yourself every detail of training neural networks. Using only Python and its math-supporting library, NumPy, you’ll train your own neural networks to see and understand images, translate text into different languages, and even write like Shakespeare! When you’re done, you’ll be fully prepared to move on to mastering deep learning frameworks.