Learn Audio Beat Tracking for Music Information Retrieval (with Python codes)

Music is all around us. Whenever we hear any music that connects to our heart and mind – we lose ourselves to it. Subconsciously, we tap along with the beats we hear. You must have noticed your foot automatically follows along with the beats of that music. There is no logical explanation as to why we do this. It’s just that we fall into the groove of the music and our mind starts to resonate with the tunes. What if we could train an artificial system that could catch the rhythm as we do? A cool application could be to build an expressive humanoid robot that runs a real-time beat tracking algorithm, enabling it to stay in sync with the music as it dances.

Image Colorization Using Optimization in Python

Colorization is a computer-assisted process of adding color to a monochrome image or movie. In the paper the authors presented an optimization-based colorization method that is based on a simple premise: neighboring pixels in space-time that have similar intensities should have similar colors. This premise is formulated using a quadratic cost function and as an optimization problem. In this approach an artist only needs to annotate the image with a few color scribbles, and the indicated colors are automatically propagated in both space and time to produce a fully colorized image or sequence. In this article the optimization problem formulation and the way to solve it to obtain the automatically colored image will be described for the images only.

Five Misconceptions about Data Science – Knowing What You Don’t Know

Data science has made its way into practically all facets of society – from retail and marketing, to travel and hospitality, to finance and insurance, to sports and entertainment, to defense, homeland security, cyber, and beyond. It is clear that data science has successfully sold its claim of ‘actionable insights from data,’ and truth be told, it often delivers on that claim, adding value that would otherwise go untapped. As a result, data science is often looked to as a panacea, a Swiss army knife, a silver bullet, a must-have, [insert your own cliché here]. This has implications for both data scientists and the organizations they work with. On one hand, data scientists are now beginning to face a new set of challenging problems, problems that even the most advanced machine learning algorithms have yet to solve: managing expectations. And on the other hand, many businesses and organizations are grappling with shifting learning curves, the latest shiny object, and the pressure to keep pace. As the data science bandwagon fills up, there are many individuals that do not fully, or even marginally, understand what data science is, what it can do, and when it is relevant. In what follows, I present what I have encountered to be five of the most common misconceptions about data science – misconceptions that will proliferate and morph as the data science wave rolls on. Recognizing these misconceptions, and avoiding the pitfalls associated with each, will go a long way toward empowering you (and your organization) when it comes to ‘deriving value from data.’

Interactive Image Segmentation with Graph-Cut in Python

In this article, interactive image segmentation with graph-cut is going to be discussed. and it will be used to segment the source object from the background in an image. This segmentation technique was proposed by Boycov and Jolli in this paper.

Finite Markov Decision Process a high-level introduction

I wanted to avoid making this post as there will be zero code. But as I assumed my series will be stand-alone I have to write it. So to move further I have to first establish a definition of Finite Markov Decision Process. It is a crucial assumption. Solving the problem of Finite Markov Decision Process (or finite MDP) is our main goal in most reinforcement learning.

Search Query Parsing

Scribd has a variety of content to offer and connecting our users with their desired content is a crucial aspect of our product. One of the main ways that users find content on Scribd is through search, and in this post I want to delve into an analysis we did regarding parsing out valuable information from a user’s query in order to better serve them relevant results, and also learn more about what they are searching for.

Genesis of AI: The First Hype Cycle

Every decade seems to have its technological buzzwords: we had personal computers in 1980s; Internet and worldwide web in 1990s; smart phones and social media in 2000s; and Artificial Intelligence (AI) and Machine Learning in this decade. However, the field of AI is 67 years old and this is the first of a series of five articles wherein:
1.This article discusses the genesis of AI and the first hype cycle during 1950 and 1982
2.The second article discusses a resurgence of AI and its achievements during 1983-2010
3.The third article discusses the domains in which AI systems are already rivaling humans
4.The fourth article discusses the current hype cycle in Artificial Intelligence
5.The fifth article discusses as to what 2018-2035 may portend for brains, minds and machines

Building a Toy Detector with Tensorflow Object Detection API

This project is second phase of my popular project -Is Google Tensorflow Object Detection API the easiest way to implement image recognition? In the original article I used the models provided by Tensorflow to detect common objects in youtube videos. These models were trained on the COCO dataset and work well on the 90 commonly found objects included in this dataset.

How neural networks learn distributed representations

Deep learning’s effectiveness is often attributed to the ability of neural networks to learn rich representations of data.

jamovi for R: Easy but Controversial

jamovi is software that aims to simplify two aspects of using R. It offers a point-and-click graphical user interface (GUI). It also provides functions that combines the capabilities of many others, bringing a more SPSS- or SAS-like method of programming to R.

What does Microsoft do with R?

I was genuinely chuffed to get a shout-out in the most recent episode of Not So Standard Deviations, the awesome statistics-and-R themed podcast hosted by Hilary Parker and Roger Peng. In that episode, Roger recounts his recent discovery of the Microsoft ecosystem of tools for R, which he (jokingly) dubbed the ‘Microsoft-verse’. While we’re flattered by the allusion to the tidyverse, in general Microsoft’s developments with R are designed to work with the entire R ecosystem rather than be distinct from it. Here’s a quick overview of what Microsoft has developed around R. It’s in three sections: the first two don’t require any special version of R, and only the third section requires a Microsoft-specific R distribution. Thanks again to Hilary and Roger for another entertaining episode of NSS Deviations and for giving me the impetus to write all of this down. (This started as an email, but I quickly realized it was getting too long and became this blog post instead.) If you have any questions or feedback, let me know in the comments section of this post.

shinyalert: Easily create pretty popup messages (modals) in Shiny

A brand new shiny package has entered the world yesterday: shinyalert. It does only one thing, but does it well: show a message to the user in a modal (aka popup, dialog, or alert box). Actually, it can do one more thing: shinyalert can also be used to retrieve an input value from the user using a modal.

Make It Happen

If you read hacker news, you’d think that deep reinforcement learning can be used to solve any problem. Deep RL has claimed to achieve superhuman performance on Go, beat atari games, control complex robotic systems, automatically tune deep learning systems, manage queueing in network stacks, and improve energy efficiency in data centers. What a miraculous technology! I personally get suspicious when audacious claims like this are thrown about in press releases, and I get even more suspicious when other researchers call into question their reproducibility. I want to take a few posts to unpack what is legitimately interesting and promising in RL and what is probably just hype. I also want to take this opportunity to argue in favor of more of us working on RL: some of the most important and pressing problems in machine learning are going to require solving exactly the problems RL sets out to solve.

Gentle Introduction to Vector Norms in Machine Learning

Calculating the length or magnitude of vectors is often required either directly as a regularization method in machine learning, or as part of broader vector or matrix operations. In this tutorial, you will discover the different ways to calculate vector lengths or magnitudes, called the vector norm.

Transform Your Data Swamp Using an Operational Data Hub

The data lake was once heralded as the answer to the flood of big data that arrived in a variety of structured and unstructured formats. But, due to the ease of integration and the lack of governance, data lakes in many companies have devolved into unusable data swamps. This short ebook from O’Reilly Media shows you how to solve this problem using an Operational Data Hub (ODH) to collect, store, index, cleanse, harmonize, and master data of all shapes and formats.

Blazing Fast EDA in R with DataExplorer

Recently, I came across this package DataExplorer that seems to be doing the entire EDA (at least, the typical basic EDA) with just one function create_report() that generates a nice presentable rendered Rmarkdown html document. That’s just a report automatically generated and what if you want the control of what you would like to perform EDA on, for which DataExplorer has got a couple of plotting functions for the same purpose. The purpose of this article is to explain how blazing fast you could EDA in R using DataExplorer Package.