Videos

See AI2's full collection of videos on our YouTube channel.
All Years
All Videos
Viewing 131-140 of 171 videos
  • Improving Structured Prediction With Locally Normalized Models Thumbnail

    Improving Structured Prediction With Locally Normalized Models

    March 25, 2016  |  Ashish Vaswani
    Locally normalized approaches for structured prediction, such as left-to-right parsing and sequence labeling, are attractive because of their simplicity, ease of training, and the flexibility in choosing features from observations. Combined with the power of neural networks, they have been widely adopted for NLP… more
  • Beyond the Distributional Hypothesis: Learning Better Word Representations Thumbnail

    Beyond the Distributional Hypothesis: Learning Better Word Representations

    March 9, 2016  |  Manaal Faruqui
    Unsupervised learning of word representations have proven to provide exceptionally effective features in many NLP tasks. Traditionally, construction of word representations relies on the distributional hypothesis, which posits that the meaning of words is evidenced by the contextual words they occur with (Harris… more
  • Deja Vu: The Story of Vision & AI Thumbnail

    Deja Vu: The Story of Vision & AI

    March 3, 2016  |  Ali Farhadi
    Ali Farhadi discusses the history of computer vision and AI.
  • Beyond Informational Retrieval Thumbnail

    Beyond Informational Retrieval

    March 2, 2016  |  Ashish Sabharwal
    Artificial intelligence and machine learning communities have made tremendous strides in the last decade. Yet, the best systems to date still struggle with routine tests of human intelligence, such as standardized science exams posed as-is in natural language, even at the elementary-school level. Can we… more
  • Strategies and Principles for Distributed Machine Learning Thumbnail

    Strategies and Principles for Distributed Machine Learning

    February 16, 2016  |  Eric Xing
    The rise of Big Data has led to new demands for Machine Learning (ML) systems to learn complex models with millions to billions of parameters that promise adequate capacity to digest massive datasets and offer powerful predictive analytics (such as high-dimensional latent features, intermediate representations… more
  • Intelligible Machine Learning Models for HealthCare Thumbnail

    Intelligible Machine Learning Models for HealthCare

    February 9, 2016  |  Rich Caruana
    Locally normalized approaches for structured prediction, such as left-to-right parsing and sequence labeling, are attractive because of their simplicity, ease of training, and the flexibility in choosing features from observations. Combined with the power of neural networks, they have been widely adopted for NLP… more
  • Probabilistic Models for Learning a Semantic Parser Lexicon Thumbnail

    Probabilistic Models for Learning a Semantic Parser Lexicon

    January 27, 2016  |  Jayant Krishnamurthy
    Lexicon learning is the first step of training a semantic parser for a new application domain, and the quality of the learned lexicon significantly affects both the accuracy and efficiency of the final semantic parser. Existing work on lexicon learning has focused on heuristic methods that lack convergence… more
  • Machine Teaching Thumbnail

    Machine Teaching

    January 12, 2016  |  Patrice Simard
    For many ML problems, labeled data is readily available. The algorithm is the bottleneck. This is the ML researcher’s paradise! Problems that have fairly stable distributions and can accumulate large quantities of human labels over time have this property: Vision, Speech, Autonomous driving. Problems that have… more
  • Adding Structure to Unstructured and Semi-structured Data Thumbnail

    Adding Structure to Unstructured and Semi-structured Data

    December 10, 2015  |  Chandra Bhagavatula
    In this talk, I will describe two systems designed to extract structured knowledge from unstructured and semi-structured data. First, I'll present an entity linking system for Web tables. Next, I'll talk about a key phrase extraction system that extracts a set of key concepts from a research article. Towards the… more
  • Provable Guarantees for Non-convex and Convex Optimization in High Dimensions Thumbnail

    Provable Guarantees for Non-convex and Convex Optimization in High Dimensions

    November 3, 2015  |  Hanie Sedghi
    Learning with big data is akin to finding a needle in a haystack: useful information is hidden in high dimensional data. Optimization methods, both convex and nonconvex, require new thinking when dealing with high dimensional data, and I present two novel solutions.