| BLOG
How To Create A Seq2Seq Network In Eager Execution With Tensorflow
Seq2Seq is a machine learning architecture based on the encoder-decoder paradigm. It is widely used for tasks such as translation, Q&A and other cases where it is desirable to produce a sequence from another....
Text Clustering Using R: Introduction For Data Scientists
Some months ago, we talked about text clustering. From supervised to unsupervised clustering, we drew a global picture of what can be done in order to make a structure emerge out of your data. Today, we will work...
Ethically designing chatbots for the future: How to not be influenced by the past
Human Bias to Data Bias Machine Learning(ML) and Artificial Intelligence(AI) revolutionize the way software is designed. Before the ML and AI days, it was humans who needed to think through and add in every...
How Computers Understand Words: A Word Vector Primer
How on earth does my computer understand words? If you think that there is a person hiding in your computer, then we have news for you! There is not. There is however, a super complex algorithm that very smart data...
Countering Internal Covariate Shift with Batch Normalization
Batch normalization is a recently developed technique to reduce training time. Sometimes, it can even improve the accuracy of a model. But what exactly is batch normalization? Simply put, it is a way to counteract...
The Information Bottleneck: Uncovering the Secret of Deep Learning?
“To think is to forget a difference, to generalize, to abstract. In the overly replete world of Funes there were nothing but details, almost contiguous details” / “Funes, The Memorious”, Jorge Luis Borges. In my...
Machine Learning Spotlight (Part 1) – How Recurrent Neural Networks Work
Recurrent Neural Networks (RNNs) quickly became the go-to neural network architecture for Natural Language Processing (NLP) tasks. In this blog post, I’ll start with a broad definition of their architecture, and...
Introduction to Information Theory and Why You Should Care
Let’s talk about information – what is it? Can we compress it and how much? What are the limits on the communication of information? We’ll try to answer these questions by looking at the revolutionary work...
The Era of Autonomous Cars: Focus on Pedestrian Detection with Deep Learning
Nowadays, we see a lot of potentially disrupting technologies. Autonomous vehicles are one of the most in vogue today! Lots of amazing things can come out of this revolution: fuel economy, reduction of cars on the...
Which Machine Learning Algorithm To Choose For My Problem?
We frequently hear about machine learning in the media, especially since the recent wave of interest in deep-learning. The perpetual improvement of machine learning techniques combined with the ever increasing...