One of the better introductions to Machine Learning I have come across till now. It is at a very high level, I must admit, but the non-mathematical intuition behind the most basic and fundamental algorithms of Machine Learning has been very nicely covered with appropriate examples. Good job, Luis Serrano. Do check out!
Gave a talk today in the Machine Learning reading group of CSE@IITB. What could have been a better choice than something hot off the press from CVPR 2016? YOLO’s claim to fame is that it is the most accurate real-time object detector and is also the fastest object detector in literature today. Here is the presentation I made. Enjoy!
I am currently in Hyderabad attending a 6-day summer school on deep learning for computer vision organized by Center for Visual Information Technology, IIIT Hyderabad. Couldn’t have asked for a better start to my PhD - with renowned speakers presenting the state-of-the-art in this space and with lots of hand on lab sessions. If you are interested in deep learning in general and in deep learning for computer vision in particular, do checkout this wonderful compilation of available resources.
According to the World Economic Forum, these technologies have potential to “transform industries, improve lives, and safeguard the planet.” The list includes some technologies that have been known for a number of years, but are only now reaching a level of maturity where their impact can be meaningfully felt: Nanosensors and the Internet of Nanothings — With the Internet of Things expected to comprise 30 billion connected devices by 2020, one of the most exciting areas of focus today is now on nanosensors capable of circulating in the human body or being embedded in construction materials.
Came across this brilliant realization of a Turing Machine - watch the video below. If you are scratching your heads, Turing Machine is a classic model embodying the very nature of computation. According to wikipedia, “A Turing machine is a hypothetical device that manipulates symbols on a strip of tape according to a table of rules. Despite its simplicity, a Turing machine can be adapted to simulate the logic of any computer algorithm, and is particularly useful in explaining the functions of a CPU inside a computer.