Interview: Thanigai Vellore, Art.com on Delivering Contextually Relevant Search Experience
We discuss the role of Analytics at Art.com, the polyglot data architecture at Art.com, the use cases for Hadoop, vendor selection, supporting semantic search and experience with Avro.
on Jul 23, 2015 in Architecture, Art.com, Avro, Hadoop, HBase, Interview, Semantic Analysis, Solr, Thanigai Vellore
Deep Learning Adversarial Examples – Clarifying Misconceptions
Google scientist clarifies misconceptions and myths around Deep Learning Adversarial Examples, including: they do not occur in practice, Deep Learning is more vulnerable to them, they can be easily solved, and human brains make similar mistakes.
on Jul 15, 2015 in Adversarial, Deep Learning, Ian Goodfellow, Myths, Regularization
Can Deep Learning Help you Find the Perfect Girl? – Part 2
Using Deep Learning to find the perfect match, PhD student Harm de Vries describes the process of data collection and analysis. Finally, the results from matching algorithm are compared to human assessment for identifying an individual's dating preferences.
on Jul 13, 2015 in Deep Learning, Love, OkCupid, Online Dating, Predictive Analytics
Can deep learning help find the perfect date?
When a Machine Learning PhD student at University of Montreal starts using Tinder, he soon realises that something is missing in the dating app - the ability to predict to which girls he is attracted. Harm de Vries applies Deep Learning to assist in the pursuit of the perfect match.
on Jul 10, 2015 in Deep Learning, ICML, Love, Machine Learning, Online Dating, Predictive Analytics
Deep Learning and the Triumph of Empiricism
Theoretical guarantees are clearly desirable. And yet many of today's best-performing supervised learning algorithms offer none. What explains the gap between theoretical soundness and empirical success?
on Jul 7, 2015 in Big Data, Data Science, Deep Learning, Mathematics, Statistics, Zachary Lipton
Data Science and Big Data: Two very Different Beasts
Creating artifact from the ore requires the tools, craftmanship and science. Same is the case of big data and data science, here we present the distinguishing factors between the ore and the artifact.
on Jul 6, 2015 in Big Data, Data Science, Sean McClure
|
| 