We introduce a new meta-learning procedure, called non-Euclidean upgrading (NEU), which learns algorithm-specific geometries by deforming the ambient space until the algorithm can achieve optimal performance. We prove that these deformations have several novel and semi-classical universal approximation properties. These deformations can be used to approximate any continuous, Borel, or modular-Lebesgue integrable functions to arbitrary precision. Further, these deformations can transport any data-set into any other data-set in a finite number of iterations while leaving most of the space fixed. The NEU meta-algorithm embeds these deformations into a wide range of learning algorithms. We prove that the NEU version of the original algorithm must perform better than the original learning algorithm. Moreover, by quantifying model-free learning algorithms as specific unconstrained optimization problems, we find that the NEU version of a learning algorithm must perform better than the model-free extension of the original algorithm. The properties and performance of the NEU meta-algorithm are examined in various simulation studies and applications to financial data.

Do large datasets provide value to psychologists? Without a systematic methodology for working with such datasets, there is a valid concern that analyses will produce noise artifacts rather than true effects. In this paper, we offer a way to enable researchers to systematically build models and identify novel phenomena in large datasets. One traditional approach is to analyze the residuals of models---the biggest errors they make in predicting the data---to discover what might be missing from those models. However, once a dataset is sufficiently large, machine learning algorithms approximate the true underlying function better than the data, suggesting instead that the predictions of these data-driven models should be used to guide model-building. We call this approach "Scientific Regret Minimization" (SRM) as it focuses on minimizing errors for cases that we know should have been predictable. We demonstrate this methodology on a subset of the Moral Machine dataset, a public collection of roughly forty million moral decisions. Using SRM, we found that incorporating a set of deontological principles that capture dimensions along which groups of agents can vary (e.g. sex and age) improves a computational model of human moral judgment. Furthermore, we were able to identify and independently validate three interesting moral phenomena: criminal dehumanization, age of responsibility, and asymmetric notions of responsibility.

In this course series we will discuss how to create and assess machine learning models. Students must have knowledge of basic statistics and basic linear algebra and Python programming. Please attend all classes within the series (101 and 102) and consider bringing a laptop. This program is in partnership with Princeton School of AI. Registration is limited to 30.

You can think of Linear Regression model as a curve fitting or function approximation model. Given a dataset $(X, y)$, the task is to find a relation $f$ between $X$ and $y$ such that $y f(X)$. We are interested in this mapping $f: X \rightarrow y$, as for any given $X$ in the future we can find $y f(X)$. If we can find any the mapping between $X$ and $y$, $y f(X)$, then its easy to predict the values of $y$ for any given $X$. So the prediction will be a line in case of 2-D data like above.

Imagine being able to know the probability of whether a persistent headache that you are experiencing is a symptom of something much worse through a simple blood test. Researchers affiliated with ClinSpec Diagnostics Limited, a spin-off from the University of Strathclyde in Glasgow, Scotland, and their colleagues developed patented technology that can detect brain cancer from blood samples. Using an innovative combination of artificial intelligence (AI) and spectroscopy, the U.K. researchers developed a method to detect brain cancer from a blood biopsy, and published their study on October 8, 2019 in Nature Communications. Headaches are one of the most common symptoms of brain tumors, according to the American Brain Tumor Association. But while headaches are very common, brain cancer is not.

Who has not heard that Bayesian statistics are difficult, computationally slow, cannot scale-up to big data, the results are subjective; and we don't need it at all? Do we really need to learn a lot of math and a lot of classical statistics first before approaching Bayesian techniques. Why do the most popular books about Bayesian statistics have over 500 pages? Bayesian nightmare is real or myth? Someone once compared Bayesian approach to the kitchen of a Michelin star chef with high-quality chef knife, a stockpot and an expensive sautee pan; while Frequentism is like your ordinary kitchen, with banana slicers and pasta pots. People talk about Bayesianism and Frequentism as if they were two different religions. Does Bayes really put more burden on the data scientist to use her brain at the outset because Bayesianism is a religion for the brightest of the brightest?

You don't need to reinvent the wheel, you need to know how to use the wheel to make your car better. The Titanic challenge hosted by Kaggle is a competition in which the goal is to predict the survival or the death of a given passenger based on a set of variables describing him such as his age, his sex, or his passenger class on the boat. I have been playing with the Titanic dataset for a while. As I'm writing this post, I am ranked 113th out of 11002 participants. You must be wondering how did I manage to achieve this.

You don't need to reinvent the wheel, you need to know how to use the wheel to make your car better. The Titanic challenge hosted by Kaggle is a competition in which the goal is to predict the survival or the death of a given passenger based on a set of variables describing him such as his age, his sex, or his passenger class on the boat. I have been playing with the Titanic dataset for a while. As I'm writing this post, I am ranked 113th out of 11002 participants. You must be wondering how did I manage to achieve this.

In the previous posts I have explained the complete derivation of EM algorithm, in this post we take a very simple example and see what all we actually need to remember to apply an EM algorithm on a clustering problem.

Imagine being able to know the probability of whether a persistent headache that you are experiencing is a symptom of something much worse through a simple blood test. Researchers affiliated with ClinSpec Diagnostics Limited, a spin-off from the University of Strathclyde in Glasgow, Scotland, and their colleagues developed patented technology that can detect brain cancer from a blood samples. Using an innovative combination of artificial intelligence (AI) and spectroscopy, the U.K. researchers developed a method to detect brain cancer from a blood biopsy, and published their study on October 8, 2019 in Nature Communications. Headaches are one of the most common symptoms of brain tumors, according to the American Brain Tumor Association. But while headaches are very common, brain cancer is not.