Talking Machines

In episode thirteen we talk with Claudia Perlich, Chief Scientist at Dstillery. We take a look at information leakage in competitions. Plus we take a listener question about trends in data size.

In episode twelve we talk with Andrew Ng, Chief Scientist at Baidu, we’re introduced to random features for large-scale kernel machines, and we take a listener question about the size of computing power in machine learning.

In episode eleven we talk with Neil Lawrence from the University of Sheffield. We learn about the Markov decision process (and what happens when they meet the real world) and take a listener question about finding insights into features in the black boxes of deep learning.

we talk with David Blei of Columbia University. We learn about Markov Chain Monte Carlo and take a listener question about using machine learning to inspire creativity in Humans

In episode nine we talk with George Dahl, a recent graduate of the University of Toronto, learn about how networks and graphs can help us understand relationships, and take a listener question about just how you find the right algorithm to solve a problem (Spoiler: start simple.)

On episode eight of Talking Machines we chat with Charles Sutton of the University of Edinburgh, Ryan introduces us to collaborative filtering, and we take a listener question on creativity in algorithms.

On this episode of Talking Machines: understanding Bayesian Non-parametrics through lunch, how much should we rely on organic intelligence models when we make machine intelligences and a conversation with Zoubin Ghahramani about his work and the Automatic Statistician

We hear the second part of our conversation with three of the pillars of machine learning Geoffrey Hinton, Yoshua Bengio, and Yann LeCun. Ryan introduces us to Deteminantal Point Processes (DPP), plus we take a listener question about function approximation as machine learning.

We hear the first part of our conversation with three of the pillars of machine learning Geoffrey Hinton, Yoshua Bengio, and Yann LeCun. Ryan introduces us to the ideas in tensor factorization methods for learning latent variable models, Plus we take a listener question about just where statistics stops and machine learning begins.

Hanna Wallach on WiML and using ML in the course of research, a listener question about scalability and big data and we learn how to pronounce (and use) Latent Dirichlet allocation

On Episode Three of Talking Machines we hear from Kevin Murphy of Google about teaching computers (and why it’s hard for them to understand why spilled milk might make you sad), and teaching humans (and why it’s hard to decide where to start). We talk about Facebook’s new open source tools, and a new way of thinking about machine learning problems. Plus we tackle a listener question about silver bullets for strong artificial intelligence.

Today on Talking Machines we talk with Google researcher Ilya Sutskever http://www.cs.toronto.edu/~ilya/ about his work. We take your questions about when programming stops and machine learning starts, and we sift through some news from the field.

Talking Machines is the place for human conversation about machine learning. Lead by hosts Katherine Gorman and Ryan Adams we explore the reality of this quickly growing field by discussing the news, taking your questions and learning from experts.