Videos tagged with Machine Learning

Google I/O 2010 - BigQuery and Prediction APIs App Engine 101 Amit Agarwal, Max Lin, Gideon Mann, Siddartha Naidu Google relies heavily on data analysis and has developed many tools to understand large datasets. Two of these tools are now available on a limited sign-up basis to developers: (1) BigQuery: interactive analysis of very large data sets and (2) Prediction API: make informed predictio...

Google I/O 2010 - BigQuery and Prediction APIs App Engine 101 Amit Agarwal, Max Lin, Gideon Mann, Siddartha Naidu Google relies heavily on data analysis and has developed many tools to understand large datasets. Two of these tools are now available on a limited sign-up basis to developers: (1) BigQuery: interactive analysis of very large data sets and (2) Prediction API: make informed predictio...

Bay Area Vision Meeting (more info below)Unsupervised Feature Learning and Deep LearningPresented by Andrew NgMarch 7, 2011ABSTRACTDespite machine learning's numerous successes, applying machine learning to a new problem usually means spending a long time hand-designing the input representation for that specific problem. This is true for applications in vision, audio, text/NLP, and other proble...

How does the human brain represent meanings of words and pictures in terms of the underlying neural activity? This talk will present our research using machine learning methods together with fMRI brain imaging to study this question. One line of our research has involved training classifiers that identify which word a person is thinking about, based on their neural activity observed using fMRI....

Active learning considers the problem of actively choosing the training data. This is particularly useful in settings where the training data is limited or comes with a price and therefore the learner needs to be "economical" in its data usage. Active learning can be particularly challenging in settings where the cost of the data varies, the learner only has partial control over the data it rec...

Author: David Richards

In this talk I'll outline our work at the University of Edinburgh to model machine translation (MT) as a probabilistic machine learning problem. Although MT systems have made large gains in translation quality in recent years, most current approaches are based on a hand engineered pipeline of disparate models linked by heuristics. I'll motivate why MT provides an interesting, but hard, structur...

EM (the Expectation Maximization algorithm) is a well known technique for unsupervised learning (where one does not have any hand labeled solutions available, but instead one must learn from the raw text). Unfortunately EM is known to fail to find good solutions in many (most?) applications on which it is tried. In this talk we present some recent work on using EM to learn how to resolve pronou...

A long-term goal of Machine Learning research is to solve highy complex "intelligent" tasks, such as visual perception auditory perception, and language understanding. To reach that goal, the ML community must solve two problems: the Deep Learning Problem, and the Partition Function Problem. There is considerable theoretical and empirical evidence that complex tasks, such as invariant...

Many users really want to find objects rather than pages. In the past few years, there has been significant progress in research in machine learning methods for information extraction (IE). I'll describe some of this progress, with a focus on recent machine learning advances in entity resolution and schema matching – with the combination of logical clauses and probability, significant gai...