Data Skeptic

In statistics, two random variables might depend on one another (for example, interest rates and new home purchases). We call this conditional dependence. An important related concept exists called conditional independence. This phrase describes situations in which two variables are independent of one another given some other variable. For example, the probability that a vendor will pay their bill on time could depend on many factors such as the company's market cap. Thus, a statistical analysis would reveal many relationships between observable details about the company and their propensity for paying on time. However, if you know that the company has filed for bankruptcy, then we might assume their chances of paying on time have dropped to near 0, and the result is now independent of all other factors in light of this new information. We discuss a few real world analogies to this idea in the context of some chance meetings on our recent trip to New York City.

Animals can't tell us when they're experiencing pain, so we have to rely on other cues to help treat their discomfort. But it is often difficult to tell how much an animal is suffering. The sheep, for instance, is the most inscrutable of animals. However, scientists have figured out a way to understand sheep facial expressions using artificial intelligence. On this week's episode, Dr. Marwa Mahmoud from the University of Cambridge joins us to discuss her recent study, "Estimating Sheep Pain Level Using Facial Action Unit Detection." Marwa and her colleague's at Cambridge's Computer Laboratory developed an automated system using machine learning algorithms to detect and assess when a sheep is in pain. We discuss some details of her work, how she became interested in studying sheep facial expression to measure pain, and her future goals for this project. If you're able to be in Minneapolis, MN on August 23rd or 24th, consider attending Farcon. Get your tickets today via https://farcon2017.eventbrite.com.

This episode collects interviews from my recent trip to Microsoft Build where I had the opportunity to speak with Dharma Shukla and Syam Nair about the recently announced CosmosDB. CosmosDB is a globally consistent, distributed datastore that supports all the popular persistent storage formats (relational, key/value pair, document database, and graph) under a single streamlined API. The system provides tunable consistency, allowing the user to make choices about how consistency trade-offs are managed under the hood, if a consumer wants to go beyond the selected defaults.

This episode discusses the vanishing gradient - a problem that arises when training deep neural networks in which nearly all the gradients are very close to zero by the time back-propagation has reached the first hidden layer. This makes learning virtually impossible without some clever trick or improved methodology to help earlier layers begin to learn.

hen faced with medical issues, would you want to be seen by a human or a machine? In this episode, guest Edward Choi, co-author of the study titled Doctor AI: Predicting Clinical Events via Recurrent Neural Network shares his thoughts. Edward presents his team’s efforts in developing a temporal model that can learn from human doctors based on their collective knowledge, i.e. the large amount of Electronic Health Record (EHR) data.

In a neural network, the output value of a neuron is almost always transformed in some way using a function. A trivial choice would be a linear transformation which can only scale the data. However, other transformations, like a step function allow for non-linear properties to be introduced. Activation functions can also help to standardize your data between layers. Some functions such as the sigmoid have the effect of "focusing" the area of interest on data. Extreme values are placed close together, while values near it's point of inflection change more quickly with respect to small changes in the input. Similarly, these functions can take any real number and map all of them to a finite range such as [0, 1] which can have many advantages for downstream calculation. In this episode, we overview the concept and discuss a few reasons why you might select one function verse another.

This episode recaps the Microsoft Build Conference.  Kyle recently attended and shares some thoughts on cloud, databases, cognitive services, and artificial intelligence.  The episode includes interviews with Rohan Kumar and David Carmona.  

Max-pooling is a procedure in a neural network which has several benefits. It performs dimensionality reduction by taking a collection of neurons and reducing them to a single value for future layers to receive as input. It can also prevent overfitting, since it takes a large set of inputs and admits only one value, making it harder to memorize the input. In this episode, we discuss the intuitive interpretation of max-pooling and why it's more common than mean-pooling or (theoretically) quartile-pooling.

This episode is an interview with Tinghui Zhou.  In the recent paper "Unsupervised Learning of Depth and Ego-motion from Video", Tinghui and collaborators propose a deep learning architecture which is able to learn depth and pose information from unlabeled videos.  We discuss details of this project and its applications.

CNNs are characterized by their use of a group of neurons typically referred to as a filter or kernel.  In image recognition, this kernel is repeated over the entire image.  In this way, CNNs may achieve the property of translational invariance - once trained to recognize certain things, changing the position of that thing in an image should not disrupt the CNN's ability to recognize it.  In this episode, we discuss a few high-level details of this important architecture.