Today, deep learning is mostly about pure supervised learning. A major drawback of supervised learning is that it requires a lot of labeled data and It is quite expensive to collect them. So, deep learning in the future is expected to unsupervised, more human-like.

Note: The video is the interview only. The audio podcast has the intro, interview, and data science learning club activity explanation.

In my imaginings, I sometimes envisage conversations between billionaires in California. The conversations that I imagine are a little like conversations among the Greek gods. For modern day California imagine Mount Olympus in the time of the Trojan wars.

This is the first time I have participated in a machine learning competition and my result turned out to be quite good: 66th out of 3303. I used R and an average of two models: glmnet and xgboost with a lot of feature engineering.

Simple image recognition app using TensorFlow and Shiny

Let’s imagine that I have ten old computer circuit boards. Eight are in perfect condition, and two are defective.

Introduction

Every year I make an annual pilgrimage to the Consumer Electronics Show in Las Vegas. |Every year I make an annual pilgrimage to the Consumer Electronics Show in Las Vegas.It was hard work but, a couple of years ago, I could just about cover the entire show in a single day; if I moved fast.Last year, there was just too much to see, so I vowed that I’d spend two days at the show this year. I stuck to that promise! This year, I attended for two days. The problem? The show has gotten bigger still. I raced around the exhibition floors for two days (with just a brief pause for a short speaking engagement), and still did not get chance to see all I wanted. This show is big (2.47 million square feet). I did not get chance to watch any of the other speakers.It’s also a busy show. I believe I heard that the attendance this year was around 170,000 people.||