Interview: Bill Moreau, USOC on Evidence-based Medicine to Reduce Sports Injuries
We discuss the success of Analytics in predicting sports injuries, recent progress in concussion management and the trends in data-driven evidence-based sports medicine.
on Mar 27, 2015 in Bill Moreau, Data Analytics, Predictive Analytics, Sports, Sports Medicine, Trends, USOC
Talking Machine – 3 Deep Learning Gurus Talk about History and Future of Machine Learning, part 1
An recent interview from the talking machine podcast with three deep learning experts. They talked about the neural network winter and its renewal.
on Mar 25, 2015 in convnet, Deep Learning, Geoff Hinton, Neural Networks, Ran Bi, Yann LeCun, Yoshua Bengio
Do We Need More Training Data or More Complex Models?
Do we need more training data? Which models will suffer from performance saturation as data grows large? Do we need larger models or more complicated models, and what is the difference?
on Mar 23, 2015 in Big Data, convnet, Generalized Linear Models, K-nearest neighbors, Training Data, Zachary Lipton
Interview: Brad Klingenberg, StitchFix on Building Analytics-powered Personal Stylist
We discuss StitchFix, how it leverages Analytics, understanding customer preferences, and pros-and-cons of involving human judgement in the recommendation process.
on Mar 20, 2015 in Analytics, Brad Klingenberg, Customer Experience, Recommendations, Stitch Fix
Small Data requires Specialized Deep Learning and Yann LeCun response
For industries that have relatively small data sets (less than a petabyte), a Specialized Deep Learning approach based on unsupervised learning and domain knowledge is needed.
on Mar 19, 2015 in Big Data, Deep Learning, Small Data, Yann LeCun
Interview: Vince Darley, King.com on the Serious Analytics behind Casual Gaming
We discuss key characteristics of social gaming data, ML use cases at King, infrastructure challenges, major problems with A-B testing and recommendations to resolve them.
on Mar 18, 2015 in A/B Testing, Analytics, Gaming, Infrastructure, King.com, Machine Learning, Predictive Analysis, Vince Darley
Deep Learning for Text Understanding from Scratch
Forget about the meaning of words, forget about grammar, forget about syntax, forget even the very concept of a word. Now let the machine learn everything by itself.
on Mar 13, 2015 in convnet, Deep Learning, Francois Petitjean, Text Classification, Torch, Yann LeCun
Deep Learning, The Curse of Dimensionality, and Autoencoders
Autoencoders are an extremely exciting new approach to unsupervised learning and for many machine learning tasks they have already surpassed the decades of progress made by researchers handpicking features.
on Mar 12, 2015 in Autoencoder, Deep Learning, Face Recognition, Geoff Hinton, Image Recognition, Nikhil Buduma
SQL-like Query Language for Real-time Streaming Analytics
We need SQL like query language for Realtime Streaming Analytics to be expressive, short, fast, define core operations that cover 90% of problems, and to be easy to follow and learn.
on Mar 12, 2015 in Real-time, Realtime Analytics, SQL, Stream Mining, Streaming Analytics
7 common mistakes when doing Machine Learning
In statistical modeling, there are various algorithms to build a classifier, and each algorithm makes a different set of assumptions about the data. For Big Data, it pays off to analyze the data upfront and then design the modeling pipeline accordingly.
on Mar 7, 2015 in Machine Learning, Mistakes, Overfitting, Regression, SVM
|
| 