Why NLP is important and it’ll be the future – our future

NLP – also known as computational linguistics – is the combination of AI and linguistics that allows us to talk to machines as if they were human.


Can Neural Networks Develop Attention? Google Thinks they Can

Trying to read this article is a complicated task from the neuroscientific standpoint. At this time you are probably bombarded with emails, news, notifications on our phone, the usual annoying coworker interrupting and other distractions that cause your brain to spin on many directions. In order to read this tiny article or perform many other cognitive tasks, you need to focus, you need attention. Attention is a cognitive skill that is pivotal to the formation of knowledge. However, the dynamics of attention have remained a mystery to neuroscientists for centuries and, just recently, that we have had major breakthroughs that help to explain how attention works. In the context of deep learning programs, building attention dynamics seems to be an obvious step in order to improve the knowledge of models and adapt them to different scenarios. Building attention mechanisms into deep learning systems is a very nascent and active area of research. A few months ago, researchers from the Google Brain team published a paper that detailed some of the key models that can be used to simulate attention in deep neural networks.


Open Source Projects by Google, Uber and Facebook for Data Science and AI

Open source is becoming the standard for sharing and improving technology. Some of the largest organizations in the world namely: Google, Facebook and Uber are open sourcing their own technologies that they use in their workflow to the public.


R-inforcement Learning Part One- Tic Tac Toe

In this first example of Reinforcement Learning in R (and C++), we’re going to train our computers to play Noughts and Crosses (or tic tac toe for Americans) to at least/super human level. Let’s get started with the libraries we’ll need. I want to stick to base for speed here, as well as obviously Rcpp. In theory you can easily generalise all the code here to any size board, but I only have tested in with 3×3 boards so YMMV.


Taking a Step Back: Here’s What AI Needs to Learn from a Child

The way babies learn is on account of an innate ability. Until now we haven’t been able to replicate this, even in complex machines. Consider artificial intelligence as a helicopter parent of the modern age that keeps a close eye on the learner and explicitly dictates them about the right and wrong. As we move forward, real technological progress will be in terms of developing a generalized system of learning for machines. Ultimately, machines must take cues from children and learn to become curious.


A Quick Guide to Create Astonishing Data Science Projects

For the last 8 years, I’ve had the privilege of leading and being a part of high performing teams in different countries and contexts. My experience building great projects and products has thought me one thing: No one has created a truly great project solo. Data Science projects and products are not an exception. Recently I worked with the other 3 team members on ‘Leveraging Data and GIS Platforms to Effectively Respond to Wildfires’. I will share some concepts and ideas that help us to move fast, together, and to create a great solution.


The Big Data Handbook

Coming from an Economics and Finance background, algorithms, data structures, Big-O and even Big Data were all too foreign to me. The terms file system, throughput, containerisation, daemons, etc. had little to no meaning in my vocabulary. Here is my attempt to explain Big Data to the man on the street (with some technical jargon thrown in for context).


Knowledge Data Science with Semantics Technologies.

An introduction to the (possible) future of data science. Welcome to a new series on data science. Here I’ll start making an introduction to some concepts and definitions that will guide our study. To understand this article, I recommend that you read these other articles I’ve written in the past:
• On Data and Science
• Building the Future of Data Science
• Ontology and Data Science
I will try to define a new beginning for our field that I’m calling: Knowledge Data Science


Top-K Off-Policy Correction for a REINFORCE Recommender System

OffKTopPolicy is now available for your usage out of the box with no prerequisites in my Reinforced Recommendation Library!


Hacking Google Coral Edge TPU: motion blur and Lanczos resize

Google’s Coral project has recently gone out of beta. According to the benchmarks, Coral devices provide excellent neural network inference acceleration for DIY makers. Those devices ground on the specialized Tensor Processing Unit ASIC (Edge TPU), which proved to be somewhat tricky to work with, but the enforced limitations and quirks are rewarding. I was eager to explore the deep internals of the interoperation between TensorFlow and Edge TPU, and to hack both to do cool, nonstandard, crazy things.
Advertisements