Featured

Hierarchy is inevitable. [Source: Google Images] As we know, the standard backpropagation algorithm is the most efficient procedure to compute the exact gradients of a loss function in a neural network … Read more

Assessing the uncertainty of predictions is elementary for business decisions. Mixture density networks help you to better understand the uncertainty you are facing in the real world. Introduction Uncertainty is a … Read more

TDS TeamBlockedUnblockFollowFollowing Feb 15 A Gentle Introduction to Graph Neural Networks (Basics, DeepWalk, and GraphSage) By 黃功詳 Steeve Huang — 8 min read Recently, Graph Neural Network (GNN) has gained increasing popularity … Read more

An Step-by-Step Guide for Building an Anti-Semitic Tweet Classifier Text + Intelligence = Gold… But, how can we mine it cheaply? Introduction There is a catch to training state-of-the-art NLP models: … Read more

This project is inspired by Drivetime Sedans case study from the book “Marketing Data Science: Modelling Techniques in Predictive Analytics with R and Python” by Thomas Miller. The author only … Read more

Some tips in finding the right target for optimization, and how to figure it out for your use case In one of his books, Isaac Asimov envisions a future where computers … Read more

I am not very passionate about art: when I visit a museum, I am a casual tourist that walks around observing paintings and sculptures, trying to learn as much as … Read more

Kaggle Days are the first global offline events series for Data Scientists and Kagglers. Such a great event provides an opportunity to both create and build the data science community. … Read more

II. Introduction to Boosting a. Concept The intuition described above can be described as such : Train the model h1 on the whole set Train the model h2 with exaggerated data on … Read more

One of the most challenging problems in modern theoretical physics is the so-called many-body problem. Typical many-body systems are composed of a large number of strongly interacting particles. Few such … Read more

AI For Cybersecurity McCarthy and Minsky described Artificial Intelligence as a task performed by a machine, which if, performed by a human instead will require a great deal of intelligence. … Read more

Valentine’s Day is arriving. Whether or not you will share this day with someone, you probably thought about how your ideal partner and relationship should look like. If you want … Read more

Can a machine think Short answer: Sure, why not. Long answer: It’s complicated. In 1950, Alan Turing, known as the father of modern computing and artificial intelligence, wondered the same thing. … Read more

Sarcasm is incredibly hard for chatbots and NLP applications. Here, we’ll take a look at why. Sarcasm or Not? As humans, you and I can look at these two chats and determine … Read more

Why thinking too much is just as bad as thinking too little. The cognitive trap Imagine you’re standing in front of your computer, much like you are now, and you’re prompted … Read more

Because who has time to write it themselves anymore? I was never any good at writing lyrics. In my high-school ska band, I wrote the horn parts and some other … Read more

Are you about thinking AI for your organization? You have identified a use case with a proven ROI? Perfect! but not so fast… do you have a data set? Well, most … Read more

Today I would like to share my experience with open source machine learning library, based on gradient boosting on decision trees, developed by Russian search engine company — Yandex. Github profile according … Read more

My last post about DCGANs was primarily focused on the idea of replacing fully connected layers with convolutions and implementing upsampling convolutions with Keras. This article will further explain the … Read more

In part 1, we looked at the theory behind Q-learning using a very simple dungeon game with two strategies: the accountant and the gambler. This second part takes these examples, … Read more

Creating model and initial training The FastAI library is designed to let you create models (FastAi calls them learners) with only a few lines of code. They provide a method called … Read more

Three Approaches to Guide You in Choosing Your Path Does your concept of a Data Scientist look something like a fictional super hero, possessing such a broad and deep skillset that … Read more

AWS SageMaker is a cloud machine learning SDK designed for speed of iteration, and it’s one of the fastest-growing toys in the Amazon AWS ecosystem. Since launching in late 2017 … Read more

Motivation : There is a lot of data out there that can be represented in the form of a graph in real-world applications like in Citation Networks, Social Networks (Followers graph, … Read more

http://www.discovery.com/tv-shows/mythbusters/about-this-show/physics-of-seesaws/ I am going to give intuitive understanding of Regularization method in as simple words as possible. Firstly, I will discuss some basic ideas, so if you think you are … Read more

Related articles: References: [1] Deep Learning Review| Yann LeCun, Yoshua Bengio, Geoffrey Hinton | http://pages.cs.wisc.edu/~dyer/cs540/handouts/deep-learning-nature2015.pdf [2] 30 Amazing Applications of Deep Learning | Yaron Hadad | http://www.yaronhadad.com/deep-learning-most-amazing-applications/ [3] Introduction to … Read more

Genetic Algorithm Configurations One of the unusual aspects to working with a GA is that it has so many settings that need to be configured. The following items can be … Read more

Machine Learning is used across many spheres around the world. The healthcare industry is no exception. Machine Learning can play an essential role in predicting presence/absence of Locomotor disorders, Heart … Read more

Scale Airflow natively on Kubernetes In the 1.10 release, Airflow introduced a new executor to run workers at scale: the Kubernetes executor. In this article we’ll look into: What is … Read more

In this article, I explain my process for collecting data, feature engineering, and using linear regression to identify predictors of active timebanks. But first… What’s a timebank? Without fail, when … Read more

This article compares several search algorithms applied to a Traveling Salesman Problem of 85 cities. The goal is to show intuition behind some well known and effective search algorithms to … Read more

As technology cozies up to the physical limits of Moore’s law, computation is increasingly limited by heat dissipation rather than the number of transistors that can be packed onto a … Read more

In the final part of this series, we predict malignancy in breast cancer tumors using the network we coded from scratch. In part 1 of this series, we understood in depth … Read more

Quantum computers, It’s a successor to the classical -digital computer, Which adds an extra dimension to existing computers which lacks in solving optimization problems & doing things in parallel. Quantum … Read more

The seminal paper of Neural Style Transfer presented by Gatys et al. [1] demonstrates a remarkable characteristic of Deep Convolutional Neural Networks. The sequential representations learned from layers of parametric … Read more

Word embeddings (e.g. word2vec, GloVe) are introduced several years ago and changing NLP tasks fundamentally. Having embeddings, we do not need one-hot encoding which causing very high-dimensional feature in most … Read more

Searching online for ONA (Organizational Network Analysis) gets you various definitions, including those with curly math symbols and graph theory. However, in a nutshell, ONA is about who communicates to … Read more

This article describes the advice and approaches on how to effectively use Kaggle as a competition platform to improve practitioner skills in Data Science with maximum efficiency and profitability. farm … Read more

Moving to San Francisco would be awesome except for the cost of rent. I use Zillow data in this project to find cheap/high-value rental opportunities in San Francisco. The following … Read more

A couple of weeks back, I gave a talk in the SFELC (San Francisco Engineering Leadership Conference). As I was preparing the slides for the talk I reflected on something … Read more

There are two more important terms related to bias and variance that we must understand now- Overfitting and Underfitting. I am again going to use a real life analogy here. … Read more

Train, validate and test partitions for out-of-time performance take planning and thought The purpose of supervised machine learning is to classify unlabeled data. We want algorithms to tell us whether a … Read more

Cross-lingual Language Model Pretraining Attention models, and BERT in particular, have achieved promising results in Natural Language Processing, in both classification and translation tasks. A new paper by Facebook AI, … Read more