Convolutional Neural Networks (CNNs): An Illustrated Explanation

Artificial Neural Networks (ANNs) are used everyday for tackling a broad spectrum of prediction and classification problems, and for scaling up applications which would otherwise require intractable amounts of data. ML has been witnessing a “Neural Revolution”1 since the mid 2000s, as ANNs found application in tools and technologies such as search engines, automatic translation, or video classification. Though structurally diverse, Convolutional Neural Networks (CNNs) stand out for their ubiquity of use, expanding the ANN domain of applicability from feature vectors to variable-length inputs.

Continue reading

Rise of the Chatbots

Almost two decades ago I saw in the arcades the futuristic fighting game “Rise of the Robots”. As a youngster I was imagining what the future of computing and robotics could be. The game ended up not being that great, regardless of that it wasn’t visually very realistic, but instead, it relied on the gameplay and partly on the player’s imagination for the immersion. Hence, around this time, I was dreaming of tablets (from Star Trek) and completely autonomous robots that would help us with everyday tasks (like terminators, without the killing part of course and maybe the Jetson’s robots?).

Yet the future was not exactly what I was expecting. After all this experimentation and technological progress, it seems that people hyped with Chatbots (or chatterbots) instead! Continue reading

From Human Brains to Computer Brains

Intelligent Systems, Artificial Intelligence, Smart Recommenders, Machine Learning and the list of endless fancy words that popup here and there over websites will always have a mystery behind. Over the past few years, we have witnessed great advancements in computer systems. Computers can now take over tasks that we, humans, never thought a computer would be able to do – including tasks that no human brain can efficiently and quickly perform such as looking through thousands of text files and drawing connections between them, reading millions of medical papers and connecting genes to potential diseases. The latter is the job of IBM Watson’s Discovery Advisor, a tool for researchers.

This way it seems that many researchers around the world strive to build computers that can substitute humans completely. The question that arises is: are we going to see computer brains that completely mimic human brains? In our post today, we cover some basics of the research in this direction trying to figure out an answer for the million cells question ..

Continue reading

R software and tools for everyday use

Long, long time ago … I started with Octave and Matlab.They were amazing and allowed me to solve a lot of interesting problems in my research. I loved the command window of Octave, but I needed the productivity an IDE gives when developing complex calculations. None of the available IDE’s for Octave were not as powerful as the Matlab IDE. The problem was that Matlab was not GNU and buying a license was very expensive. Then, I found R and I realized that none Octave neither Matlab were the tool I needed for my research. I needed advanced project and file management through repositories, fast data manipulation, an easy way to export my calculations, a creative way of authoring reports and a powerful IDE that let me access my beloved command window. Now R gives me all I need and is an important part of my everyday toolbox. For those who does not known R, I must say that R is a well known programming language that is widely used on mathematics, economy, biology… Its main benefits includes the ability to work easily with statistics and data manipulation. R is very popular on academics and research, is GNU, very powerful and have a lot of packages that allows do magical things in a few clicks or with a few commands.

Continue reading