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

Weekly Selection – Jan 5, 2018

Information Planning and Naive Bayes


by Vadim Smolyakov – 7 min read

Information planning involves making decisions based on information measures. **** Information planning is closely related to active learning [1] and optimum experiment design [2] in which labeled data is expensive to obtain.


Web based voice command recognition

by Boris Smus – 7 min read.

Last time we converted audio buffers into images. This time we’ll take these images and train a neural network using deeplearn.js. The result is a browser-based demo that lets you speak a command ("yes" or "no"), and see the output of the classifier in real-time.


Artistic Style Transfer

by Firdaouss Doukkali – 5 min read.

This article is about Artistic Style Transfer or you can call it Neural Style Transfer too. It is interesting to know that deep learning can make some magical things with images. So, I’ll try to give you a better understanding of this concept and how it works.


Understanding Feature Engineering (Part 1) – Continuous Numeric Data

by Dipanjan Sarkar – 18 min read

Any intelligent system basically consists of an end-to-end pipeline starting from ingesting raw data, leveraging data processing techniques to wrangle, process and engineer meaningful features and attributes from this data. Then we usually leverage techniques like statistical models or machine learning models to model on these features and then deploy this model if necessary for future usage based on the problem to be solved at hand.


Probability concepts explained: Maximum likelihood estimation

by Jonny Brooks-Bartlett – 8 min read

In this post I’ll explain what the maximum likelihood method for parameter estimation is and go through a simple example to demonstrate the method. Some of the content requires knowledge of fundamental probability concepts such as the definition of joint probability and independence of events.


Artificial Intelligence, AI in 2018 and beyond

by Eugenio Culurciello – 13 min read

These are my opinions on where deep neural network and machine learning is headed in the larger field of artificial intelligence, and how we can get more and more sophisticated machines that can help us in our daily routines.


Politicizing Mass Shootings – When we can talk about Gun Control

by Viet Vu – 2 min read

On October 1st, 2017, a gunman rained bullets from a hotel room in Las Vegas, killing 59 and injuring 546. It was the deadliest mass shooting in US’s recent history. After every mass shooting, the narrative has become familiar, almost scripted.


Build a Taylor Swift detector with the TensorFlow Object Detection API, ML Engine, and Swift

by Sara Robinson – 11 min read

Note: as of this writing there is no official TensorFlow library for Swift, I used Swift to build the client app for prediction requests against my model. This may change in the future, but Taylor has the final say on that.


10 Machine Learning Algorithms You need to Know

by Sidath Asiri – 6 min read

We live in a start of revolutionized era due to development of data analytics, large computing power, and cloud computing. Machine learning will definitely have a huge role there and the brains behind Machine Learning is based on algorithms..


do GANs really model the true data distribution, or are they just cleverly fooling us?

by Gal Yona – 6 min read

Since their introduction in 2014, Generative Adversarial Networks (GANs) have become a popular choice for the task of density estimation. The approach is simple: A GAN framework is composed of two networks, one for generating new samples, and another for discriminating between real samples (from the true data distribution) and generated samples.


GPU Optimized dynamic programming

by Anuradha Wickramarachchi – 3 min read

Let us consider the Path sum: two ways in project euler problem 81 (Link). It is an interesting problem for us to explore the dynamic programming paradigm and GPU optimization of the solution.


Training and Visualising Word Vectors

by Priya Dwivedi – 6 min read

In this tutorial I want to show how you can implement a skip gram model in tensorflow to generate word vectors for any text you are working with and then use tensorboard to visualize them. I found this exercise super useful to i) understand how skip gram model works and ii) get a feel for the kind of relationship these vectors are capturing about your text before you use them downstream in CNNs or RNNs.


An Introduction to GPU Optimization

by Anuradha Wickramarachchi – 5 min read

Most of the tasks that involve heavy computations take time and it becomes further time consuming as the datasets get bigger and bigger. One way of addressing this problem is using threads.


Looking at German Traffic Signs

by Kasper Fredenslund – 10 min read

I mean, sure, they are there when we drive through Germany, and we do (hopefully) see them, and sometimes we even register their meaning, and alter our behavior based on those meanings. But we don’t do nearly enough looking at those bold, blue, red, and white, geometrical pictograms.


We thanks our 39 Patreon supporters for making our work possible 😊

William Hogg, Chris Seidel, Ramesh Shalam, Daniel Shapiro, PhD, Venkat Raman, Formulated.by, Kirill Panarin, Sai Sai, Zach Thigpen, Tirthajyoti Sarkar, Anthony Manello, Naveen Tirupattur.

Become a Patron


Related Articles