31
32
33
Building a natural description of images
Posted by Google Research Scientists Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan“Two pizzas sitting on top of a stove top oven”...
34
35
36
Recommending music on Spotify with deep learning
An overview of what I've been doing as part of my internship at Spotify in NYC this summer: using convolutional neural networks for audio-based music recommendation.
37
On Google's Acquisition of Nest
Google’s Nest acquisition has very little to do with selling thermostats and smoke detectors in particular. Instead, it’s about Google having the ability to do consumer hardware right, in general.
38
Evolutionary algorithms and analog electronic circuits
I've been working for a while on a program that automatically generates analog electronic circuits using evolutionary algorithms. It's still very much a work in progress, but I've used it to generate some useful circuits. Current workings of the program is as follows: Programmer decides a goal function, possible…
39
Microsoft OCR Library for Windows Runtime
This blog was written by Jelena Mojasevic, Program Manager at Microsoft. We are pleased to announce that Microsoft OCR Library for Windows Runtime has been released as a NuGet package. The library empowers you to easily add text recognition capabilities in your Windows Phone 8/8.1 and Windows 8.1 Store apps. OCR…
40
Hostile AI: You're soaking in it
I was in a Facebook discussion about “Friendly Artificial Intelligence” — this is a buzzword from the Singularity Institute people. They be...
41
Mistakes Programmers Make when Starting in Machine Learning
There is no right way to get into machine learning. We all learn slightly different ways and have different objectives of what we want to do with or for machine learning. A common goal is to get productive with machine learning quickly. If that is your goal then this post highlights five common mistakes programmers […]
42
43
44
Hacking Hearthstone with machine learning – Defcon talk wrap-up
A wrap-up of my Defcon talk about hacking Hearthstone with machine learning including slides and a video.
45
AIs are now re-writing history
Dr Robert Smith is a technologist, complexity scientist, entrepreneur, writer and sought-after public speaker. He is an artificial intelligence (A.I.) expert and has worked with clients, companies and institutions across the private and public sectors. Having grown up in Alabama at the height of the Civil Rights…
46
47
Naive Bayes and Text Classification I – Introduction and Theory
Naive Bayes classifiers, a family of classifiers that are based on the popular Bayes’ probability theorem, are known for creating simple yet well performing…
48
How a mathematician constructed a decision tree to solve a medical problem
Here’s an excerpt from Love and Math, a book by Edward Frenkel. The author writes about mathematics and his career. One of the stories is about …
49
A Gentle Introduction to Backpropagation
A gentle introduction to backpropagation, a method of programming neural networks
50
51
PredictionIO – open source machine learning for predictive features
PredictionIO is an open source machine learning server for software developers to create predictive features, such as personalization, recommendation and content discovery. Building a production-grade engine to predict users’ preferences ...
52
53
54
55
56
57
Why I Am Not An Integrated Information Theorist (or, The Unconscious Expander)
Happy birthday to me! Recently, lots of people have been asking me what I think about IIT—no, not the Indian Institutes of Technology, but Integrated Information Theory, a widely-discussed &#…