MLconf 2016 Seattle
| title | author | length |
|---|---|---|
| Can Cognitive Neuroscience Provide a Theory of Deep Learning... | Ted Willke | 43m |
Claims that biological brains limit multitasking because shared, reused representations cause interference lead to concrete measurements: convert tasks to an… | ||
| Iron: Keyword Grouping Model for Text Ads Bidding in Paid Search | Suxin Guo | 08m |
Iron trains a Gradient Boosting Machine on eBay search features, paid-search performance and Google feedback to predict per-keyword conversion rates, then… | ||
| How Can We Trust Machine Learning? Exploration, Evaluation... | Carlos Guestrin | 23m |
Companies use GraphLab Create to train a recommender in minutes and ship it to AWS as a real‑time microservice via Predictive Services (demo uses a 3‑node… | ||
| An Information Theoretic Metric for Multi-Class Categorization | Sam Steingold | 23m |
Presentation slides: http://www.slideshare.net/SessionsEvents/sam-steingold-lead-data-scientist-magnetic-media-online-at-mlconf-sea-52016
An Information… | ||
| Practical Probabilistic Programming with Figaro | Avi Pfeffer | 24m |
A mature probabilistic programming library implemented as Figaro in Scala provides a Scala-embedded model representation and inference engines; it runs… | ||
| Multi-algorithm Ensemble Learning at Scale: Software... | Erin Ledell | 20m |
Scalable stacking implementation called H2O Ensemble combines deep nets, GBMs, random forests and others into a metalearner and runs distributed across… | ||
| When Recommendations Systems Go Bad | Evan Estola | 24m |
Covers concrete failures: a hotel recommender that split Mac vs PC users after finding Mac sessions more likely to book 4–5 star hotels (three alternative… | ||
| Generating a Billion Personal News Feeds | Ewa Dominowska | 22m |
Facebook ranks feed for 1 billion users across hundreds of billions of posts by retrieving and scoring candidates in real time, targeting under 200… | ||
| Discovering Unwarranted Associations in Data-Driven... | Florian Tramèr | 26m |
FairTest is a Python toolkit integrated into SciPy that automatically finds statistically significant unwarranted associations by treating an application as a… | ||
| Can AI Become a Dystopian Threat to Humanity? – A Hardware... | Igor Markov | 17m |
Argument says future AI danger is constrained by physical limits not runaway cognition so practical defenses focus on hardware and resources rather than… | ||
| Smarter Search With Spark-Solr | Jake Mannix | 22m |
Open-source spark-solr library provides a Solr-backed RDD/DataFrame so Spark reads and writes directly to Solr, letting teams store all data in Solr (no… | ||
| Disambiguating Explicit and Implicit Geographic References... | Jason Baldridge | 30m |
Builds language models over a KD-tree adaptive grid and uses hierarchical logistic regression to score cells, plus simple smoothing and beam search for fast… | ||
| Declarative Programming for Statistical ML | Kristian Kersting | 19m |
RELOOP is a declarative mathematical programming language embedded in Python that lets users write convex optimization problems before knowing domain… | ||
| Scaling Data Science Products, Not Data Science Teams | Amanda Casari | 21m |
Concur scales products into new countries without hiring more data scientists by shipping a single codebase with configurable features to segregated data… | ||
| nothing matches | ||