Humor is a very human phenomenon. Can a machine appreciate humor? This reminds me of a scene from the 1994 movie “Star Trek: Generations” where the android Lt. Commander Data discovers humor. After having his emotion chip activated, Data finds everything amusing.
I am convinced we’re at an important inflection point in the timeline of the discipline of computer science. When compared to other disciplines like mathematics, physics and biology, computer science is a very young field, starting around 1964. But something is happening now, in 2014, that is propelling the field into a new evolutionary period.
The “How Machine Learning Works” lecture series concludes by developing some machine learning python code from scratch. We use real valued numbers sampled from two different Gaussians with different priors.
“Altiscale offers the first cloud service purpose-built to run Apache Hadoop. We run the latest version of Hadoop on custom infrastructure, augmented with Apache Hive, Pig, and Oozie, and with first-class support for Python, R, and Ruby. Altiscale’s infrastructure is faster, more reliable, easier to use, and more affordable than alternatives.”
The “How Machine Learning Works” lecture series continues by building on top of the Bayesian classifier developed in Part 3 of the series. We’ll build an expectation-maximization (EM) algorithm that locally maximizes the likelihood function.
“Big data techniques offer a way to analyze data pooled across many patients: their specific disease mutations, biological markers, the treatments, and outcomes — in order to identify unexpected ways that existing therapies can be applied and combined to create personalized treatments that dramatically improve the chances of survival.”
The “How Machine Learning Works” lecture series continues to build on Bayes rule that was taught last time. We’ll define training and testing data sets and build a Bayesian classifier.
“Map-D uses multiple NVIDIA GPUs to interactively query and visualize big data in real-time. Map-D is an SQL-enabled column store that generates 70-400X speedups over other in-memory databases. This talk discusses the basic architecture of the system, the advantages and challenges of running queries on the GPU, and the implications of interactive and real-time big data analysis in the social sciences and beyond.”