by | Released June 2015 | ISBN: 9781491931080

Push the envelope of data science by exploring emerging topics such as data management, machine learning, natural language processing, crowdsourcing, and algorithm design with this O'Reilly video collection—taken from the Hardcore Data Science sessions at Strata + Hadoop World 2015 in San Jose, California.This video collection includes:Beyond DNNs towards New Architectures for Deep Learning, with Applications to Large Vocabulary Continuous Speech RecognitionTara Sainath, Researcher, GoogleDNNs were first explored for acoustic modeling, where numerous research labs demonstrated improvements in WER between 10-40% relative. This session provides an overview of the latest improvements in deep learning across various research labs since the initial inception.On the Computational and Statistical Interface and "Big Data"Michael Jordan, Professor, UC BerkeleyHow does statistical decision theory provide a mathematical point of departure for achieving such a blending? In this session, you'll learn theoretical tradeoffs between statistical risk, amount of data, and “externalities” such as computation, communication, and privacy.Interpretable Machine Learning in PracticeMaya Gupta, Research and Development Manager, GoogleWhat makes a large machine learning system more interpretable and robust in practice? This session discusses the importance of monotonicity, smoothness, semantically meaningful inputs and outputs, and designing algorithms that are easy to debug.Visual Understanding Beyond NamingAlyosha Efros, Associate Professor, UC BerkeleyThis session describes some of the efforts to bypass the “language bottleneck” and other information to help in visual understanding and visual data mining.Finding Repeated Structure in Time Series Data: Commercial and Scientific OpportunitiesEamonn Keogh, Professor, University of California - RiversideIn this session, Eamonn argues that, relative to other types of data (text, social networks, etc.), time series data is relatively underexploited, and that many opportunities are available for novel commercial applications and scientific discoveries.Tensor Methods for Large-scale Unsupervised Learning: Applications to Topic and Community ModelingAnima Anandkumar, Faculty member, UC IrvineUnderstand how to exploit tensor methods for learning. Tensors are higher order generalizations of matrices, and are useful for representing rich information structures. Tensor factorization involves finding a compact representation of the tensor using simple linear and multilinear algebra.High Performance Machine Learning through Codesign and RoofliningJohn Canny, Professor, UC BerkeleyHow fast can machine learning (ML) and graph algorithms be? BIDMach is a toolkit for machine learning that uses rooflined design and GPUs to achieve one-to-three orders of magnitude improvements over other toolkits on single machines—larger than have been reported for cluster systems running on hundreds of nodes for common ML tasks.A Quest for Visual Intelligence in ComputersFei-Fei Li (Stanford University)Look into computer vision technology, including ongoing projects in large-scale object recognition and visual scene story telling from Stanford Vision Lab.Graph mining for log dataDavid Andrzejewski, Lead Data Sciences Engineer, Sumo LogicMany of the millions of events logged inside a given software system are not isolated occurrences, but rather links in richly interconnected causal chains. This session reveals how graph-mining techniques can surface high-value insights from the relationships between logged events.Why Julia is Important for Data ScienceJohn Myles White, Data Scientist, FacebookIn this session, you'll learn the ways in which Julia improves upon the current generation of languages used for data science.Drugs, DNA, and Dinosaurs: Building High Quality Knowledge Bases with DeepDiveChris Re, Assistant Professor, Stanford UniversityLearn how DeepDive is used in a range of tasks from diagnosing rare diseases to drug purposing to filling out the tree of life. DeepDive helps to create knowledge bases that meet—and sometimes exceed—human-level quality and to perform predictive analytics on top of this data. Show and hide more Publisher resources View/Submit Errata

1. Introduction - Hardcore Data Science California 2015 - Ben Lorica 00:01:07
2. Beyond DNNs towards New Architectures for Deep Learning, with Applications to Large Vocabulary Continuous Speech Recognition - Tara Sainath 00:34:05
3. On the Computational and Statistical Interface and "Big Data" - Michael Jordan 00:48:48
4. Interpretable Machine Learning in Practice - Maya Gupta 00:26:24
5. Visual Understanding Beyond Naming - Alyosha Efros 00:36:31
6. Finding Repeated Structure in Time Series Data: Commercial and Scientific Opportunities - Eamonn Keogh 00:21:25
7. Tensor Methods for Large-scale Unsupervised Learning: Applications to Topic and Community Modeling - Anima Anandkumar 00:31:09
8. High Performance Machine Learning through Codesign and Rooflining - John Canny 00:31:10
9. A Quest for Visual Intelligence in Computers - Fei-Fei Li 00:29:39
10. Graph Mining for Log Data - David Andrzejewski 00:27:59
11. Why Julia's Important for Data Science - John Myles White 00:24:37
12. Drugs, DNA, and Dinosaurs: Building High Quality Knowledge Bases with DeepDive - Chris Re 00:30:20
Show and hide more



9781491931080.hardcore.data.science.OR.part1.rar

9781491931080.hardcore.data.science.OR.part2.rar

9781491931080.hardcore.data.science.OR.part3.rar