Igor Muniz
Director of AI
Others
All Themes
Featured
Porto Seguro Challenge - 2nd Place Solution
We are pleased to announce that we got second place in the Porto Seguro
Challenge, a competition organized by the largest insurance company in Brazil.
Porto Seguro challenged us to build an algorithm to identify potential buyers of
their products. If you are interested in knowing how to do the same and still
discover the secrets that led us to second place, read on below!
Introduction
In this problem, Porto Seguro provided us with data of users who bought or did
not buy one of its products. T
Igor MunizOctober 26, 2021
Distributed learning in an on-premise cluster - A Kaggle Reinforcement Learning case
Have you tried any distributed learning algorithms? If you are just starting out
in this area, I have my doubts, but if you have been on this path for a few
years, you might have faced one of those models. The incredible development of
the machine learning area in the last decade has not only brought a new state of
the art to several problems but has also taken processing optimization and
parallelization to another level. With increasingly larger models, any common
machine or even a single sup
Igor MunizJanuary 08, 2021
Stay in The Loop!Subscribe to receive Artificial Intelligence content that will help you perform better.
Don't worry, we don't SPAM. Ever.
Don't worry, we don't SPAM. Ever.
Articles
Porto Seguro Challenge - 2nd Place Solution
We are pleased to announce that we got second place in the Porto Seguro
Challenge, a competition organized by the largest insurance company in Brazil.
Porto Seguro challenged us to build an algorithm to identify potential buyers of
their products. If you are interested in knowing how to do the same and still
discover the secrets that led us to second place, read on below!
Introduction
In this problem, Porto Seguro provided us with data of users who bought or did
not buy one of its products. T
Igor MunizOctober 26, 2021
VGGNets are backIf you have studied the deep learning timeline history, you may know that the
big moment was in 2012 when Alex Krizhevsky presented a deep convolutional
architecture able to improve the state-of-the-art error on ImageNet dataset by
11%. After that, it was proved that deep learning era had come.
Two years later a better architecture was proposed by Karen Simonyan and Andrew
Zisserman from the University of Oxford. In this model, the main difference was
the number of layers, where they have s
Igor MunizJune 03, 2021
Calculating Material Stress Using Deep LearningIf you are an engineer or get some classes of its subjects in college, you know
resistances of material can give you a huge headache!
Determining the stress a material is under, for example, requires complex
equations created by mathematicians, engineers, and physicists. Such difficult
that most part of the time we need computers to solve it. However, it seems that
MIT researchers discovered a new method to simplify our lives, and guess what,
using AI of course!
By applying some computer visio
Igor MunizApril 27, 2021
Nvidia GTC 2021Nvidia's annual GTC starts today and you don't want to lose this opportunity.
Every year Nvidia comes to show their exciting advancements in GPU technology
and as artificial intelligence is directly linked to GPUs, you should expect a
lot of AI content there, becoming a paradise for data scientist, machine
learning engineers, and AI enthusiasts. You can also watch content about
automation, health care, and quantum computing, all for free. But if you have
extra money, I will recommend doing a wor
Igor MunizApril 12, 2021
Potatoes Cluster: Training a Deep Learning Model Using a 100 Potatoes
Have you ever heard about battery potatoes? Did you know that it is also
possible to process information using potatoes? In this post we are going to
show you how it’s possible to create a cluster of potatoes, that not only serves
as a power supply but also processes data in a very cheap way. With that, we
could achieve the performance of a Nvidia GTX 1060 using 100 potatoes connected
with nails and clips.
Building the Cluster
In order to build our cluster, we are going to need some other item
Igor MunizApril 01, 2021
Distributed learning in an on-premise cluster - A Kaggle Reinforcement Learning case
Have you tried any distributed learning algorithms? If you are just starting out
in this area, I have my doubts, but if you have been on this path for a few
years, you might have faced one of those models. The incredible development of
the machine learning area in the last decade has not only brought a new state of
the art to several problems but has also taken processing optimization and
parallelization to another level. With increasingly larger models, any common
machine or even a single sup
Igor MunizJanuary 08, 2021
Multi-task learning: Solving different computer vision problems with a single model
In the last few years, significant improvements in computer vision were made,
making it possible to obtain important information from images. Some of the
challenges for a better understanding of a scene are the detection of people and
the recognition of the activities they are performing. In this post, I'm going
to show a method that I proposed to do a single end-to-end model able to detect
people, estimate their pose, and recognize each one of their activities by their
pose.
Figure 1: Result
Igor MunizNovember 12, 2020
7 common mistakes of a machine learning beginner
In recent years, the term Artificial Intelligence has gained strength and
together with it have emerged some professions such as Data Scientist and
Machine Learning Engineer. Knowing and applying machine learning is attractive
and appears to be the path to success. However this path can be troubled and
especially discouraging for those who are just starting out. Over the years
working as a Data Scientist and Machine Learning Researcher, I have witnessed
several common mistakes that made life di
Igor MunizOctober 15, 2020