The world’s leading publication for data science, AI, and ML professionals.

Weekly Selection – Dec 29, 2017

Audio features for web-based ML


By Boris Smus – 8 min read.

One of the first problems presented to students of deep learning is to classify handwritten digits in the MNIST dataset. This was recently ported to the webthanks to deeplearn.js.


A Zero-Math Introduction to Markov Chain Monte Carlo Methods

By Ben Shaver – 11 min read.

For many of us, Bayesian statistics is voodoo magic at best, or completely subjective nonsense at worst. Among the trademarks of the Bayesian approach, Markov chain Monte Carlo methods are especially mysterious.


The promise of AI in audio processing

by Daniel Rothmann – 7 min read

2017 has been a good year for AI, deep learning in particular. We have seen a rise of AI technologies for image and video processing. Even though things tend to take a little while longer making it to the world of audio, here we have also seen impressive technological advances.


One-Shot Learning: Face Recognition using Siamese Neural Network

by Firdaouss Doukkali – 5 min read

This article is about One-shot learning especially Siamese Neural Network using the example of Face Recognition. I’m going to share with you what I learned about it from the paper FaceNet: A Unified Embedding for Face Recognition and Clustering and from deeplearning.ai.


Machine learning fundamentals (II): Neural networks

By Conor McDonald – 6 min read

In my previous post I outlined how machine learning works by demonstrating the central role that cost functions and gradient descent play in the learning process.


How to Create a Codenames Bot Part 1: Word2vec

by Jeremy Neiman – 6 min read

As a board game enthusiast and programmer, it occurred to me that designing an algorithm to play the popular game Codenames would be an interesting, if not worthy endeavor. In this series of blog posts I will share my various attempts at generating the word association-based clues that are integral to Codenames. So! Let’s get started.


Stylometric Analysis: Satoshi Nakamoto

by Michael Chon— 7 min read

Natural Language Processing tools were applied to the Satoshi Nakamoto’s Bitcoin paper to compare it to numerous cryptocurrency-related papers in an attempt to identify the true identity of the unknown Satoshi Nakamoto.


How to visualize distributions

by Marc Laforet – 5 min read

You have munged all the necessary data into a clean format, you’ve appropriately performed a snazzy statistical analysis and now it’s time to analyze the results. This is where visualizing your data comes in handy.


What if I told you database indexes could be learned?

by Cody Marie Wild – 5 min read

This paper is one that I unfortunately missed getting to see presented at NIPS, but which has been getting quite a lot of attention in ML circles in the last few days. The authors, who count among their number Jeff Dean, a very well-respected and early-days Google employee, have one core point, that they reiterate throughout the paper: at their heart, database indexes are models.


Data Mining in Brief

by Sidath Asiri – 4 min read

Data mining is a very popular topic nowadays. Unlike a few years ago, everything is bind with data now and we are capable of handling these kinds of large data well.


We thanks our Patreon supporters for making our work possible 😊

Daniel Shapiro, PhD, Venkat Raman, Formulated.by, Kirill Panarin, Sai Sai, Zach Thigpen, Tirthajyoti Sarkar, Anthony Manello, Naveen Tirupattur.

Become a Patron


Related Articles