The Machine Learning Lover’s Holiday Book List

Holiday Booklist

In the market for some last-minute gift recommendations for a machine learning “geek?” (we use the term affectionately around here). DefinedCrowd’s got you covered with our “machine learning lover’s book list,” hand-selected by our ML Team. From the ins and outs of speech and language processing to broad-level theoretical overviews of the machine learning field, these texts cover the wide-ranging topics we discuss in our office every day. Enjoy! And happy holidays from all of us at DefinedCrowd.

Speech and Language Processing An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition by Daniel Jurafsky

Summary: In this excellent intro to speech and language processing tecnologies, Jurafsky presents an empirical approach that comprehensively covers language technology based on applying statistical and machine-learning algorithms alongside modern technologies. The book largely emphasizes scientific evaluation and practical applications.

Foundations of Statistical Natural Language Processing by Christopher D. Manning and Hinrich Schütze

Summary:
A fantastic introduction to statistical natural language processing that uses an analytical approach to cover a range of mathematical and linguistic foundations for NLP technologies. Foundations of Statistical Natural Language Processing proves further useful in presenting theoretical and algorithmic building blocks for NLP technologies.

Crowdsourcing for Speech Processing: Applications to Data Collection, Transcription and Assessment by Maxine Eskenazi, Gina-Anne Levow, Helen Meng, Gabriel Parent and David Suendermann

Summary: An essential read for anyone interested in learning more about crowdsourcing training data for speech models. Offers a comprehensive overview from the basics of setting up a task, to tips for task interfaces and methodologies for quality assessment.

Deep Learning (Adaptive Computation and Machine Learning series) by Ian Goodfellow, Yoshua Bengio, Aaron Courville and Francis Bach

Summary:
This book offers a great introduction to what many consider the “Holy Grail” of Machine Learning.
Topics covered, range from mathematical and conceptual background to deep learning techniques. The “research perspectives” that book-end chapters with specific case-studies make Deep Learning a great resource for students and software engineers alike.

Deep Learning for Computer Vison with Python by Adrian Rosebrock

Summary: For those looking to master deep learning for image recognition and classification, Deep Learning for Computer Vision offers practical walk-throughs, hands-on tutorials and a direct teaching style. Useful for both beginners and for the seasoned deep learning pro looking to brush up on the fundamentals.