| BLOG
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...
How we kinda sorta just added computer vision to chatbots
This is a story of opportunity. This is one of those jaw dropping moments, where you look at the person in front of you and say “oh my, now THAT IS AN IDEA!”. First, a bit of background: we are collaborative...
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...
Introduction to text clustering
In this article I’m going to describe a pipeline for Text Clustering. I could not find any satisfactory explanation, so I decided to share my findings after a few weeks of research about this task. In a previous...
Towards an augmented Dataset
In my previous blog, I wrote about the importance of dataset but how can we simply create a trustworthy source of knowledge that suits our needs?
Understanding words to understand language
Every day, our brains do gymnastics with words and their meanings to understand language, what are the solutions to do it programmatically?