Featured

Whether your model is meant to be explanatory or predictive has profound implications for its design Someone somewhere right now is building a model. Many, many people in fact. Whether for … Read more

https://www.wired.com/2016/12/2016-year-deep-learning-took-internet/ In recent times, Deep Learning has created a significant impact in the field of computer vision, natural language processing, and speech recognition. Due to the large amounts of data … Read more

TL;DR The imminent danger with Artificial Intelligence has nothing to do with machines becoming too intelligent. It has to do with machines inheriting the stupidity of people. Background Whom should … Read more

Since 2016 I have been working on the Antispam team of a dating and social platform, where my goal is to build solutions to detect spammers and avoid the proliferation … Read more

Now, let’s take a look at how we can resist adversarial samples via thresholding. Suppose the input image (from class 1) has been adversarially perturbed to fool the encoder into … Read more

Researchers came up with the concept of CNN or Convolutional Neural Network while working on image processing algorithms. Traditional fully connected networks were kind of a black box — that took in … Read more

Dealing with dependencies in data. What is this all about? My hope with this post is to provide a conceptual overview of how to deal with a specific type of dataset commonly … Read more

The Progressively-Growing GAN architecture released from NVIDIA and published at ICLR 2018 has become the primary display of impressive GAN image synthesis. Classically, GANs have struggled to output low- and … Read more

How Meteorites are Studied The scientists scan meteorites using an electron microprobe (EMP). An EMP shoots a beam of electrons at the meteorite. When the beam of electrons collides with the … Read more

How to implement a Word2vec model with Python and NumPy Introduction Recently, I have been working with several projects related to NLP at work. Some of them had something to do … Read more

Foreground Segmentation using FCN + Edge Detection Using HED + Object Detection Using Faster R-CNN Gland Haematoxylin and Eosin (H&E) stained slides and ground truth labels Foreground Segmentation using FCN + Edge … Read more

Less than a year ago, with its GP102 chip + 3584 CUDA Cores + 11GB of VRAM, the GTX 1080Ti was the apex GPU of last-gen Nvidia Pascal range (bar … Read more

A Salt Identification Case Study Table of Contents: Introduction Prerequisites What is Semantic Segmentation? Applications Business Problem Understanding the data Understanding Convolution, Max Pooling and Transposed Convolution UNET Architecture and Training … Read more

Music plays an integral part of most of our lives. It is the common language that helps us express ourselves when no words could describe how we feel. Music also … Read more

This week, I got a bit of time to play around with two new (to me) data journalism tools that have been on my radar. The first was an out-of-the-box data … Read more

1. CONFERENCE At the Rework Deep Learning Conference I want to start with conferences because I just came back from one in January 2019. This is probably the most expensive … Read more

Artificial Intelligence Artificial Intelligence is fundamentally a statistical approach to architecture. The premise of AI, that blends statistical principles with computation is a new approach that can improve over the … Read more

How to successfully prepare your data for a machine learning model in minutes Data preprocessing is the first (and arguably most important) step toward building a working machine learning model. It’s … Read more

WHY Implicit data?Because we as lazy users, barely submit ratings (explicit data) for anything we do on any platform, be it Netflix, Amazon, LinkedIn etc. WHAT we do, is just watch … Read more

Easy right? — Figuring out that the above picture represents the digit four, was no deal for you. You didn’t even bother about the poor resolution of the image, how amazing. We … Read more

Recurrent Neural Networks are networks which persist information. They are useful for sequence related tasks like Speech Recognition, Music Generation, etc. However, RNN’s suffer from short-term memory. If a sequence … Read more

An approximate proportion of academic articles on Google Scholar that both contain “bodies” and “spaces” in a scientific, mathematical or medical context, or in a patent. Behind this graph is … Read more

Image from https://www.tradingsetupsreview.com/trading-charts-without-time-range-tick-volume/ In a series of articles I was applying a very straightforward approach to forecast financial time series: take the whole dataset, using a sliding window approach generate … Read more

What is BERT? How does one use BERT to solve problems? Google Colab, Tensorflow, Kubernetes on Google Cloud Overview This for people who want to create a REST service using a … Read more

Neon sign showing the simple statement of Bayes’ theorem. Courtesy: Wikipedia Bayes’ Theorem Having just explored what the Conditional Probability is, let’s take a look at the Bayes’ Theorem. It … Read more

source Learning from Demonstration Reinforcement learning bears a lot of promise for the future; recent achievements have shown its ability in solving problems at super human level, like playing board … Read more

A brief introduction to the future of healthcare You and I have 3 billion things in common. Or close to it anyway. And it’s not just you and I, everyone … Read more

“Technical Strategy for AI Engineers, In the Era of Deep Learning” Machine Learning Yearning is about structuring the development of machine learning projects. The book contains practical insights that are … Read more

Meditations on AI, Reinforcement Learning and the Extended Phenotype Discussions on the interplay of humans and Artificial Intelligence tend to pose the issue in the language of opposition. However, according … Read more

Know your data, where it comes from, what’s in it, what it means. It all starts from there. If there is one piece of advice that I consistently give to … Read more

Okay, maybe a little math Monte Carlo Casino and Garden, Monaco Monte Carlo simulations are extremely common methods in the world of data science and analytics. They can be used for … Read more

Introduction to image restoration using deep image prior. In this post, I will mainly be focusing on task of image restoration and how deep image prior can be used to solve … Read more

Office of Science and Technology Policy Logo, US Government Work (public domain) It happened. Did you miss it? On February 11th 2019, the administration issued an Executive Order on Maintaining American Leadership … Read more

This time, we will examine what homoscedastic, heteroscedastic, epistemic, and aleatoric uncertainties actually tell you. In my opinion, this is an upcoming research field in Bayesian deep learning and has … Read more

OpenAI Masters Many Natural Language Tasks with a Single Unsupervised Model Natural language understanding(NLU) is one of the richest areas in deep learning which includes highly diverse tasks such as … Read more

Combine numerical features and text review to build up a classification model (Neural Network, Xgboost, Logistic) Tom LinBlockedUnblockFollowFollowing Feb 15 0. Abstract 0.1 The Incentive The purpose of this post … Read more

MaherBlockedUnblockFollowFollowing Feb 15 There is a 5-Step shortcut that you can do to be able to solve machine learning problems right away, As a beginner, you can take this path … Read more

In the first part, you learned about trends and seasonality, smoothing models and ARIMA processes. In this part, you’ll learn how to deal with seasonal models and how to implement … Read more

I have been working with Tensorflow during last months and I realized that, although there is a large number of Github repositories with many different and complex models, is hard … Read more