Featured

We provide here XY Universe: a 2D particle survival environment for training your Deep Reinforcement Learning agents to stay alive as long as possible by avoiding collisions with “bad” particles. … Read more

Over the last few years, the exponential progress in the fields of machine and deep learning have a spun a new way to solve some of healthcare’s most plaguing problems: … Read more

An accurate response to one of the First-World’s most annoying problems. We’ve all been there: You want to change your cell phone plan, or figure out why your damn TV … Read more

I only have data about myself, of course, but I’m very curious about other developers. Are there developers with little variance, and each day they work on their main project … Read more

The Dictionary Action-Value Function: See Q-Value. Actions: Actions are the Agent’s methods which allow it to interact and change its environment, and thus transfer between states. Every action performed by … Read more

Based on some recent conversations, I realized that text preprocessing is a severely overlooked topic. A few people I spoke to mentioned inconsistent results from their NLP applications only to … Read more

As a start to this small community based science experiment, I provide access to Latimer’s data and initial exemplar R code. This is by no means exhaustive, as the intent … Read more

So… What is Git? Git is a distributed version-control system for tracking changes in source code during software development — Wikipedia Looking at this definition given by Wikipedia, I was once … Read more

If you’re an engineer in the self-driving space, you frequently get asked variations of the same question. “Why is it taking so long?” one might say. “Wasn’t I supposed to … Read more

Building the Pipeline Below is a summary of the various preprocessing and modeling steps. The high-level steps include: Preprocessing: load and examine data, cleaning, tokenization, padding Modeling: build, train, and test … Read more

The Spark GraphFrame is a powerful abstraction for processing large graphs using distributed computing. It provides a plethora of common graph algorithms including label propagation and PageRank. Further, it provides … Read more

Training, Visualizing, and Making Predictions with Decision Trees Decision trees are the most important elements of a Random Forest. They are capable of fitting complex data sets while allowing the user … Read more

Showing different types of SQL joins with a pandas dataframe SQL can be a little intimidating when you’ve never used it before. You’ll hear people talking about complex joins between … Read more

Why and How You Can Write Python Programs that Automatically Analyze Scientific Data Sets Teaching Each Other New Coding Skills Everybody reading Towards Data Science is likely familiar with the typical application … Read more

aka “Will’s Rules”, without which your project doesn’t have a chance in … As you have likely heard or experienced, not all technology projects manage to proceed from inception to design … Read more

Photo by Felix Mittermeier on Unsplash On the most important job nearly no one has The last six months were, in many ways, some of the best of my professional life. My … Read more

Credit: Disney | ABC Television Group Introduction As evidenced in the outpouring of articles from major entertainment news outlets in the last month since the nominations were announced, predicting the … Read more

Or why data scientists at small and new companies should pay special attention to non-technical work Photo by Samuel Zeller on Unsplash A few days ago, I read Randy Au’s Medium … Read more

I know AI… gimme gimme This morning I was sipping my usual espresso before starting the day, peacefully browsing LinkedIn posts, when I came across the nth+1 article authored by a … Read more

Different Ways to Handle Imbalanced Datasets. Classification is one of the most common machine learning problems. The best way to approach any classification problem is to start by analyzing and … Read more

SCImago Journal Rank (SJR indicator) is a measure of scientific influence of scholarly journals that accounts for both the number of citations received by a journal and the importance or … Read more

Solving the Mountain Car environment using Q-learning. This is the third in a series of articles on Reinforcement Learning and Open AI Gym. Part 1 can be found here, while … Read more

A complete guide to K-means clustering algorithm Photo by Ankush Minda on Unsplash Let’s say you want to classify hundreds (or thousands) of documents based on their content and topics, or … Read more

Have you ever heard of the Turing test? Turing test is a test designed by Alan Turing in 1950 to see whether a machine can exhibit conversational behaviours that are … Read more

A lot of people love Harden, even more, can’t stand his game. But he is having one of the most impressive seasons in modern basketball. He is posting amazing numbers … Read more

You’re walking around in the office you’ve spent so many hours working hard, drinking coffee and playing pingpong with colleagues. All of a sudden, a threatening shadow appears. You turn … Read more

How To Handle This Mess We can’t handle that mess without first handling a single vector! If you look at many generalizations done in mathematics, you’ll find they primarily utilize matrices. … Read more

The Challenge is Human-Computer-Interaction, not Algorithms DanijelBlockedUnblockFollowFollowing Feb 21 Artificial intelligence (AI) is one of the most hyped terms in the 21st century, and yet one of the most misunderstood. … Read more

Instagram comments are more important than you think Today, more than ever, consumers are able to connect and voice their opinions about their favourite brands through social media. As a result, … Read more

Doing cool things with data! Introduction Object Detection in Aerial Images is a challenging and interesting problem. With the cost of drones decreasing, there is a surge in amount of aerial … Read more

Learn the fundamentals of deep learning and build your very own neural network for image classification Photo by Aron Visuals on Unsplash The “what” and the “why” What is deep learning We have … Read more

SVM with tf-idf vectors edges out LSTM in quality and performance for classifying the 20-newsgroups text corpus. Document is a specific sequence of words. But not all sequences of words … Read more

Ensuring fairness and safety in artificial intelligence(AI) applications is considered by many the biggest challenge in the space. As AI systems match or surpass human intelligence in many areas, it … Read more

‘SLAM’ refers to the method of simultaneous localisation (i.e. position/orientation of) some sensor with respect to its surroundings, while at the same time mapping the environment.This is an active area … Read more

The #1 Goal in Ride-Hailing: Allocation Grab’s ride-hailing business in its simplest form is about matchmaking Passengers looking for a comfortable mode of transport and Drivers looking for a flexible … Read more

Investigating concerns of numerical imprecision Really cross, and full of entropy… In neuronal networks tasked with binary classification, sigmoid activation in the last (output) layer and binary crossentropy (BCE) as the … Read more

3. Train on Multi Agents Scenario — A2C The modules/functions used to build up A2C model are as follows, A2CModel: Neural network for A2C reinforcement learning algorithm. collect_trajectories(): Collect n-step experience transitions. … Read more

This article about AI in fintech services is originally written for Django Stars blog. Just as many other technological advancements, Artificial Intelligence came to our lives from the pages of … Read more

3. Train on a Single Agent Scenario — DDPG 3.1 DDPG First, I import some self-defined modules to configure the whole setting before training starts. The [modules] include, ddpg_model: Module file containing … Read more

How to optimize your time with the help of Computer Science Everyone knows how it feels like to procrastinate. Despite its bad reputation though, procrastination is in fact an optimized algorithm. … Read more

Summary of the kaggle.com Micro Course Recently, I did the micro course Machine Learning Explainability on kaggle.com. I can highly recommend this course as I have learned a lot of useful … Read more