November 17, 2017

In this week's episode, host Kyle Polich interviews author Lance Fortnow about whether P will ever be equal to NP and solve all of life's problems. At the heart of the P-NP problem is the question "are there problems for which the answers can be checked by computers, but not found in a reasonable time?" If there are such problems, then P does not equal NP. However, if all answers can be found easily as well as checked (if only we found out how) then P equals ... View More >

November 10, 2017
Sudoku in NP

by Kyle Polich

or the title as I prefer it to rende... View More >

November 3, 2017

In this episode, Professor Michael Kearns from the University of Pennsylvania joins host Kyle Polich to talk about the computational complexity of machine learning, complexity in game theory, and algorithmic fairness. Michael's doctoral thesis gave an early broad overview of computational learning theory, in which he emphasizes the mathematical study of efficient learning algorithms by machines or computational syste... View More >

October 27, 2017
Turing Machines

by Kyle Polich

TMs are an model of computation at the heart of algorithmic analysis. A Turing Machine has two components. An infinitely long piece of tape (memory) with re-writable squares and a read/write head which is programed to change it's state as it processes the input. This exceptionally simple mechanical computer can compute anything that is intuitively computable, thus says the Church-Turing The... View More >

October 22, 2017

John Wilmes is a postdoctoral researcher in the Algorithms and Randomness Center at the Georgia Institute of Technology. He received his Ph.D. in Mathematics in 2016 from the University of Chicago, where he worked under the supervision of László Babai ba bai as a NSF Graduate Research Fellow. John's research interests lie in discrete math and the theory of comput... View More >

October 19, 2017

John Wilmes... View More >

October 13, 2017
Big Oh Analysis

by Kyle Polich

How long an algorithm takes to run depends on many factors including implementation details and hardware. However, the formal analysis of algorithms focuses on how they will perform in the worst case as the input size grows. We refer to an algorithm's runtime as it's "O" which is a function of it's input size "n". For example, $O(n)$ represents a linear algorithm - one that takes roughly twice as long to run if you double the input size. In this episode we discuss a few everyday examples of algorithmic analysis including sorting, search a shuffled deck of cards, and verifying if a grocery list was successfully comple... View More >

October 6, 2017

In this episode, Microsoft's Corporate Vice President for Cloud Artificial Intelligence, Joseph Sirosh, joins host Kyle Polich to share some of the Microsoft's latest and most exciting innovations in AI development platforms. Last month, Microsoft launched a set of three powerful new capabilities in Azure Machine Learning for advanced developers to exploit big data, GPUs, data wrangling and container-based model deployme... View More >

September 29, 2017

Last year, the film development and production company End Cue produced a short film, called Sunspring, that was entirely written by an artificial intelligence using neural networks. More specifically, it was authored by a recurrent neural network called long short-term memory (LSTM). According to End Cue's Chief Technical Officer, Deb Ray, the company has come a long way in improving the generative AI aspect of the bot. In this episode, Deb joins host Kyle Polich to discuss how generative AI models are being applied in creative processes, such as screenwriting. Their discussion also explores how data science for analyzing development projects, such as financing and selecting scripts, as well as optimizing the content production proce... View More >

September 22, 2017
One Shot Learning

by Kyle Polich

One Shot Learning is the class of machine learning procedures that focuses learning something from a small number of examples. This is in contrast to "traditional" machine learning which typically requires a very large training set to build a reasonable mo... View More >

September 15, 2017

A deep dive on Recommender Systems with Joseph Konstan in our first live episode ever, which took place at FARCon 2017.... View More >

September 8, 2017

A Long Short Term Memory (LSTM) is a neural unit, often used in Recurrent Neural Network (RNN) which attempts to provide the network the capacity to store information for longer periods of time. An LSTM unit remembers values for either long or short time periods. The key to this ability is that it uses no activation function within its recurrent components. Thus, the stored value is not iteratively modified and the gradient does not tend to vanish when trained with backpropagation through time.... View More >

September 1, 2017
Zillow Zestimate

by Kyle Polich

Zillow is a leading real estate information and home-related marketplace. We interviewed Andrew Martin, a data science Research Manager at Zillow, to learn more about how Zillow uses data science and big data to make real estate predictions.... View More >

August 25, 2017

Our guest Pranav Rajpurkar and his coauthored recently published Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks, a paper in which they demonstrate the use of Convolutional Neural Networks which outperform board certified cardiologists in detecting a wide range of heart arrhythmias from ECG d... View More >

August 18, 2017

RNNs are a class of deep learning models designed to capture sequential behavior. An RNN trains a set of weights which depend not just on new input but also on the previous state of the neural network. This directed cycle allows the training phase to find solutions which rely on the state at a previous time, thus giving the network a form of memory. RNNs have been used effectively in language analysis, translation, speech recognition, and many other ta... View More >

August 11, 2017
Project Common Voice

by Kyle Polich

In this week's episode, guest Andre Natal from Mozilla joins our host, Kyle Polich, to discuss a couple exciting new developments in open source speech recognition systems, which include Project Common Voice.... View More >

August 4, 2017

A Bayesian Belief Network is an acyclic directed graph composed of nodes that represent random variables and edges that imply a conditional dependence between them. It's an intuitive way of encoding your statistical knowledge about a system and is efficient to propogate belief updates throughout the network when new information is ad... View More >

July 28, 2017

by Kyle Polich

In this episode, Tony Beltramelli of UIzard Technologies joins our host, Kyle Polich, to talk about the ideas behind his latest app that can transform graphic design into functioning code, as well as his previous work on spying with wearab... View More >

July 21, 2017

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 varia... View More >

July 14, 2017

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.... View More >

July 7, 2017
Cosmos DB

by Kyle Polich

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 defau... View More >

June 30, 2017

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-propogation has reached the first hidden layer. This makes learning virtually impossible without some clever trick or improved methodology to help earlier layers begin to le... View More >

June 23, 2017
Doctor AI

by Kyle Polich

When 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.... View More >

June 9, 2017
Ms Build 2017

by Kyle Polich

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 interiews with Rohan Kumar and David Carm... View More >

June 9, 2017
Activation Functions

by Kyle Polich

desc... View More >

June 2, 2017
Max Pooling

by Kyle Polich

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-pool... View More >

May 26, 2017

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 an deep learning architecture which is able to learn depth and pose information from unlabeled videos. We discuss details of this project and it's applicati... View More >

May 18, 2017

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 architect... View More >

May 12, 2017

In this episode, Arnab Ghosh and Viveka Kulharia from Oxford University join Kyle in a lively discussion on one of the major pitfalls in generative adversarial networks-- mode collapse. Arnab and Viveka share a solution to tackle this problem.... View More >

May 5, 2017

GANs are an unsupervised learning method involving two neural networks iteratively competing. The discriminator is a typical learning system. It attempts to develop the ability to recognize members of a certain class, such as all photos which have birds in them. The generator attempts to create false examples which the discriminator incorrectly classifies. In successive training rounds the networks examine each and play a mini-max game of trying to harm the performance of the ot... View More >